Papers

Field

Top tools here

Open problems in 3D scene

High-quality novel view synthesis under large viewpoint changes3 papers raise it · 4 address it
Feed-forward 3D Gaussian Splatting struggles to maintain rendering quality when camera poses differ significantly from training views.
- InfiniSplat v2: Analyzing and Improving Feed-Forward 3DGS from Any Viewsraises · addresses
- LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generationraises · addresses
- NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesisraises · addresses
- FineSplat: Fine Patches, Local Groups, Detailed Splatsaddresses
3D geometric consistency in generated videos2 papers raise it · 3 address it
Video generators often produce visually appealing but geometrically inconsistent 3D worlds, breaking spatial coherence.
- Orbia: Do Generated Videos Form a Consistent 3D World?raises · addresses
- GeoFix: Geometry Fixing for 4D Consistent Generationraises · addresses
- OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphsaddresses
Fine-grained geometry and appearance recovery in feed-forward 3DGS2 papers raise it · 2 address it
Existing feed-forward methods fail to capture small-scale details and high-frequency textures in 3D scenes.
- FineSplat: Fine Patches, Local Groups, Detailed Splatsraises · addresses
- InfiniSplat v2: Analyzing and Improving Feed-Forward 3DGS from Any Viewsraises · addresses
Dynamic scene modeling with physically plausible object interactions2 papers raise it · 2 address it
Static 3D scenes lack motion, and dynamic methods often ignore physical constraints between objects.
- OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphsraises · addresses
- Tetris3D: 3D Scene Generation With Objects That Fit Togetherraises · addresses
Efficient real-time rendering for mobile 3D Gaussian Splatting1 paper raises it · 1 addresses it
Deploying 3DGS on mobile devices is limited by storage, computation, and redundant primitives.
- Mobile-4DGS: Unified Static-Dynamic Real-time Mobile Gaussian Splattingraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Topics in this field

3d scene · 3d reconstruction · depth estimation279 papers37 this week
gaussian splatting 3dgs · 3d gaussian splatting · feed forward 3d215 papers26 this week
remote sensing · satellite imagery · earth observation135 papers22 this week
small target detection · infrared small target · target detection124 papers18 this week
camera lidar · 3d object detection · point clouds99 papers15 this week
point cloud registration · 3d point clouds · point cloud72 papers12 this week

Topics in this field

Active contributors · 90 days

Active contributors

Activity · 12 weeks

Activity

Recent papers

All papers in Research

arXiv cs.CVSep 21
MIND the Gap: A Geographic Implicit Neural Representation with Adjustable Spatial Scale
Isaac Corley, Arjun Rao, Esther Rolf, Konstantin Klemmer, Evan Shelhamer +5
Geographic measurements are often sparse, leaving large areas without labels for the quantities we want to map. Geographic implicit neural representations (INRs) provide coordinate-based embeddings that can be combined with sparse labels to predict at unsampled locations without satellite imagery at inference. Yet existing INRs are largely evaluated with random holdouts, leaving their ability to generalize across larger geographic gaps unclear. We introduce Matryoshka Implicit Neural Distillation (MIND), a geographic INR whose spatial granularity can be adjusted after training. MIND distills several pretrained geospatial models using nested supervision at increasing embedding dimensions, dividing the representation into contiguous chunks. Early chunks capture broad spatial patterns, while later chunks add increasingly local variation. Downstream models can retain only the leading chunks or use our Chunked Penalty to reduce reliance on later chunks without retraining the INR. We also introduce CoordBench, comprising $52$ datasets and $78$ targets with both random and regional holdouts at multiple spatial scales. Across CoordBench, fine-scale features help most when labels are…
PDF arXiv
arXiv cs.ROSep 21
PARTE: Plane-Assisted Robust Transformation Estimation for Point Cloud Registration
Abolfazl Babanazari, Carson Cramer, Tyler Summers, Carlos Nieto, Kaveh Fathian
Global point-cloud registration remains challenging when limited overlap, repetitive geometry, and sensor noise produce correspondence sets dominated by outliers. Planar regions are particularly difficult for conventional point descriptors and are therefore often suppressed or discarded before matching. We present PARTE (Plane-Assisted Robust Transformation Estimation), a global registration method that instead treats planar structure as complementary registration evidence. PARTE extracts planar patches and represents them using our novel Plane Context Histogram (PCH), a descriptor that encodes the geometry surrounding each patch, while a two-level matching procedure identifies reliable plane correspondences. Candidate point and plane correspondences are combined in a confidence-weighted compatibility graph for joint outlier rejection, followed by rigid transformation estimation. When no usable plane correspondences are available, PARTE naturally reduces to point-only registration. We evaluate PARTE on 8,097 registration pairs across six indoor and outdoor benchmarks spanning dense RGB-D and sparse LiDAR measurements. Evaluations show PARTE achieves the highest overall success…
PDF arXiv
arXiv cs.ROSep 21
GINIO: A Geometric SO(3)-Equivariant Interface for Neural Inertial Odometry
Chankyo Kim, Minghan Zhu, Tzu-Yuan Lin, Avantika Rattan, Maani Ghaffari
Neural inertial odometry increasingly uses networks as learned measurements inside filtering pipelines. Such measurements should transform consistently under arbitrary IMU mounting conventions: their mean must transform as a vector, and their covariance must transform congruently as a second-order tensor. We present GINIO, a geometric SO(3)-equivariant interface for neural inertial odometry under arbitrary rotations of the IMU measurement frame. Given calibrated IMU windows, our framework predicts a motion measurement and uncertainty obeying these tensorial laws. To support efficient sensor-frame learning, we introduce Last-Frame Alignment (LFA), a deterministic preprocessing step that is provably equivalent to world-frame training for SO(3)-equivariant predictors. The connected estimator tracks sensor-local states such as IMU bias, separating nuisance estimation from the geometric law enforced by the learned measurement. We instantiate the same interface in filter-connected NIO, AirIO-style recurrent aerial prediction, EqNIO-style full-SO(3) canonicalization, and ResNet-style temporal backbones. On TLIO, GINIO achieves 2.018 m ID/SO(3) ATE while EqNIO degrades to 76.389 m, using…
PDF arXiv
arXiv cs.ROSep 21
Beyond the Flat Seafloor: A Closed-Form Two-View Constraint to Aid Sidescan Sonar Reconstruction
Kalin Norman, Joshua G. Mangelson
Sidescan sonar is a common sensor for both manned and autonomous marine exploration and mapping, yet very few methods build upon or exploit the geometric projection model of the sensor. As sidescan sonar is limited to a 1D range measurement, many approximations are frequently used, including the long-standing assumption of a flat seafloor. Rather than make similar approximations, this paper focuses on a multi-view geometry based approach and formalizes a two-view geometric constraint and proves that a shared feature is constrained to a locus within the intersection of a sphere and a plane. In addition, we characterize what governs the size of the ambiguity locus through Monte Carlo simulation that is grounded in real aperture and mounting geometry for both a surface vessel and an underwater vehicle. We translate additional simulations of relative trajectories for both vehicle platforms into concrete survey-planning guidance. Our results show that locus length is strongly governed by elevation misalignment, and peaks at a moderate oblique crossing angle of approximately 20 degrees, with minimal locus lengths obtained at near parallel and anti-parallel passes.
PDF arXiv
arXiv cs.CVSep 21
Geometric and Semantic Coupling for Interaction Understanding in 3D Scenes
Hanyang Kong, Xingyi Yang
Understanding interaction in a 3D scene requires recovering movable parts, their motion, and where they can be operated. These quantities are related, and their predictions can inform one another. A closed cabinet door, for instance, reveals a movable surface but may leave the hinge side ambiguous; its handle helps resolve this ambiguity, while the part provides context for localizing and interpreting the small handle. Building on this observation, we present SEGMENT-SNAP, which combines geometric and semantic evidence through part-handle coupling. Three independently trained predictors recover movable parts, dense handles, and part-associated handle proposals. We couple their outputs in two directions. For part motion, a training-free geometric decoder fits predicted part surfaces under explicit physical priors and uses detected handles to select candidate hinge lines. For handle prediction, a part-conditioned branch proposes additional handles, while standalone part classes refine their rotation/translation labels, with dense-handle labels as a fallback. Each transfer is applied once, without iterative feedback. On the Articulate3D validation set, handle guidance raises…
PDF arXiv
arXiv cs.CVSep 21
WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory
Wangbo Yu, Kunhao Liu, Wenbo Hu, Shenghai Yuan, Chaoran Feng +6
Video world models enable interactive exploration of dynamic environments, yet struggle to respect prior observations over long horizons and across viewpoints. We present WorldCrafter, a video world model that learns a camera-queryable implicit 3D-aware memory for this purpose. The key insight is to let the requested viewpoint shape how multi-view evidence is compressed into the video generator's limited token budget. Trained jointly with the video generator, a memory encoder and pose-conditioned readout module integrate historical observations into a fixed set of target view-specific tokens before denoising, without explicit depth-based correspondences. By combining this memory with recent temporal context and few-step distillation, WorldCrafter enables streaming scene exploration from a single input image or text prompt. Experiments across static and dynamic scenes show substantial gains in long-horizon consistency and camera-control accuracy while preserving visual quality during minute-scale exploration.
PDF arXiv

Papers

Topics in this field

3d scene · 3d reconstruction · depth estimation279 papers37 this week
gaussian splatting 3dgs · 3d gaussian splatting · feed forward 3d215 papers26 this week
remote sensing · satellite imagery · earth observation135 papers22 this week
small target detection · infrared small target · target detection124 papers18 this week
camera lidar · 3d object detection · point clouds99 papers15 this week
point cloud registration · 3d point clouds · point cloud72 papers12 this week

Active contributors · 90 days

Recent papers

All papers in Research

arXiv cs.CVSep 21
MIND the Gap: A Geographic Implicit Neural Representation with Adjustable Spatial Scale
Isaac Corley, Arjun Rao, Esther Rolf, Konstantin Klemmer, Evan Shelhamer +5
Geographic measurements are often sparse, leaving large areas without labels for the quantities we want to map. Geographic implicit neural representations (INRs) provide coordinate-based embeddings that can be combined with sparse labels to predict at unsampled locations without satellite imagery at inference. Yet existing INRs are largely evaluated with random holdouts, leaving their ability to generalize across larger geographic gaps unclear. We introduce Matryoshka Implicit Neural Distillation (MIND), a geographic INR whose spatial granularity can be adjusted after training. MIND distills several pretrained geospatial models using nested supervision at increasing embedding dimensions, dividing the representation into contiguous chunks. Early chunks capture broad spatial patterns, while later chunks add increasingly local variation. Downstream models can retain only the leading chunks or use our Chunked Penalty to reduce reliance on later chunks without retraining the INR. We also introduce CoordBench, comprising $52$ datasets and $78$ targets with both random and regional holdouts at multiple spatial scales. Across CoordBench, fine-scale features help most when labels are…
PDF arXiv
arXiv cs.ROSep 21
PARTE: Plane-Assisted Robust Transformation Estimation for Point Cloud Registration
Abolfazl Babanazari, Carson Cramer, Tyler Summers, Carlos Nieto, Kaveh Fathian
Global point-cloud registration remains challenging when limited overlap, repetitive geometry, and sensor noise produce correspondence sets dominated by outliers. Planar regions are particularly difficult for conventional point descriptors and are therefore often suppressed or discarded before matching. We present PARTE (Plane-Assisted Robust Transformation Estimation), a global registration method that instead treats planar structure as complementary registration evidence. PARTE extracts planar patches and represents them using our novel Plane Context Histogram (PCH), a descriptor that encodes the geometry surrounding each patch, while a two-level matching procedure identifies reliable plane correspondences. Candidate point and plane correspondences are combined in a confidence-weighted compatibility graph for joint outlier rejection, followed by rigid transformation estimation. When no usable plane correspondences are available, PARTE naturally reduces to point-only registration. We evaluate PARTE on 8,097 registration pairs across six indoor and outdoor benchmarks spanning dense RGB-D and sparse LiDAR measurements. Evaluations show PARTE achieves the highest overall success…
PDF arXiv
arXiv cs.ROSep 21
GINIO: A Geometric SO(3)-Equivariant Interface for Neural Inertial Odometry
Chankyo Kim, Minghan Zhu, Tzu-Yuan Lin, Avantika Rattan, Maani Ghaffari
Neural inertial odometry increasingly uses networks as learned measurements inside filtering pipelines. Such measurements should transform consistently under arbitrary IMU mounting conventions: their mean must transform as a vector, and their covariance must transform congruently as a second-order tensor. We present GINIO, a geometric SO(3)-equivariant interface for neural inertial odometry under arbitrary rotations of the IMU measurement frame. Given calibrated IMU windows, our framework predicts a motion measurement and uncertainty obeying these tensorial laws. To support efficient sensor-frame learning, we introduce Last-Frame Alignment (LFA), a deterministic preprocessing step that is provably equivalent to world-frame training for SO(3)-equivariant predictors. The connected estimator tracks sensor-local states such as IMU bias, separating nuisance estimation from the geometric law enforced by the learned measurement. We instantiate the same interface in filter-connected NIO, AirIO-style recurrent aerial prediction, EqNIO-style full-SO(3) canonicalization, and ResNet-style temporal backbones. On TLIO, GINIO achieves 2.018 m ID/SO(3) ATE while EqNIO degrades to 76.389 m, using…
PDF arXiv
arXiv cs.ROSep 21
Beyond the Flat Seafloor: A Closed-Form Two-View Constraint to Aid Sidescan Sonar Reconstruction
Kalin Norman, Joshua G. Mangelson
Sidescan sonar is a common sensor for both manned and autonomous marine exploration and mapping, yet very few methods build upon or exploit the geometric projection model of the sensor. As sidescan sonar is limited to a 1D range measurement, many approximations are frequently used, including the long-standing assumption of a flat seafloor. Rather than make similar approximations, this paper focuses on a multi-view geometry based approach and formalizes a two-view geometric constraint and proves that a shared feature is constrained to a locus within the intersection of a sphere and a plane. In addition, we characterize what governs the size of the ambiguity locus through Monte Carlo simulation that is grounded in real aperture and mounting geometry for both a surface vessel and an underwater vehicle. We translate additional simulations of relative trajectories for both vehicle platforms into concrete survey-planning guidance. Our results show that locus length is strongly governed by elevation misalignment, and peaks at a moderate oblique crossing angle of approximately 20 degrees, with minimal locus lengths obtained at near parallel and anti-parallel passes.
PDF arXiv
arXiv cs.CVSep 21
Geometric and Semantic Coupling for Interaction Understanding in 3D Scenes
Hanyang Kong, Xingyi Yang
Understanding interaction in a 3D scene requires recovering movable parts, their motion, and where they can be operated. These quantities are related, and their predictions can inform one another. A closed cabinet door, for instance, reveals a movable surface but may leave the hinge side ambiguous; its handle helps resolve this ambiguity, while the part provides context for localizing and interpreting the small handle. Building on this observation, we present SEGMENT-SNAP, which combines geometric and semantic evidence through part-handle coupling. Three independently trained predictors recover movable parts, dense handles, and part-associated handle proposals. We couple their outputs in two directions. For part motion, a training-free geometric decoder fits predicted part surfaces under explicit physical priors and uses detected handles to select candidate hinge lines. For handle prediction, a part-conditioned branch proposes additional handles, while standalone part classes refine their rotation/translation labels, with dense-handle labels as a fallback. Each transfer is applied once, without iterative feedback. On the Articulate3D validation set, handle guidance raises…
PDF arXiv
arXiv cs.CVSep 21
WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory
Wangbo Yu, Kunhao Liu, Wenbo Hu, Shenghai Yuan, Chaoran Feng +6
Video world models enable interactive exploration of dynamic environments, yet struggle to respect prior observations over long horizons and across viewpoints. We present WorldCrafter, a video world model that learns a camera-queryable implicit 3D-aware memory for this purpose. The key insight is to let the requested viewpoint shape how multi-view evidence is compressed into the video generator's limited token budget. Trained jointly with the video generator, a memory encoder and pose-conditioned readout module integrate historical observations into a fixed set of target view-specific tokens before denoising, without explicit depth-based correspondences. By combining this memory with recent temporal context and few-step distillation, WorldCrafter enables streaming scene exploration from a single input image or text prompt. Experiments across static and dynamic scenes show substantial gains in long-horizon consistency and camera-control accuracy while preserving visual quality during minute-scale exploration.
PDF arXiv

Activity · 12 weeks

Open problems in 3D scene

High-quality novel view synthesis under large viewpoint changes3 papers raise it · 4 address it
Feed-forward 3D Gaussian Splatting struggles to maintain rendering quality when camera poses differ significantly from training views.
- InfiniSplat v2: Analyzing and Improving Feed-Forward 3DGS from Any Viewsraises · addresses
- LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generationraises · addresses
- NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesisraises · addresses
- FineSplat: Fine Patches, Local Groups, Detailed Splatsaddresses
3D geometric consistency in generated videos2 papers raise it · 3 address it
Video generators often produce visually appealing but geometrically inconsistent 3D worlds, breaking spatial coherence.
- Orbia: Do Generated Videos Form a Consistent 3D World?raises · addresses
- GeoFix: Geometry Fixing for 4D Consistent Generationraises · addresses
- OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphsaddresses
Fine-grained geometry and appearance recovery in feed-forward 3DGS2 papers raise it · 2 address it
Existing feed-forward methods fail to capture small-scale details and high-frequency textures in 3D scenes.
- FineSplat: Fine Patches, Local Groups, Detailed Splatsraises · addresses
- InfiniSplat v2: Analyzing and Improving Feed-Forward 3DGS from Any Viewsraises · addresses
Dynamic scene modeling with physically plausible object interactions2 papers raise it · 2 address it
Static 3D scenes lack motion, and dynamic methods often ignore physical constraints between objects.
- OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphsraises · addresses
- Tetris3D: 3D Scene Generation With Objects That Fit Togetherraises · addresses
Efficient real-time rendering for mobile 3D Gaussian Splatting1 paper raises it · 1 addresses it
Deploying 3DGS on mobile devices is limited by storage, computation, and redundant primitives.
- Mobile-4DGS: Unified Static-Dynamic Real-time Mobile Gaussian Splattingraises · addresses

Named by an AI from these papers' abstracts.

Fields · AI · updated 4m ago

3D scene

Found by the topic model: 3d scene, gaussian splatting 3dgs, remote sensing.

130papers this week−28.2% vs last week

All papers · 924 With code · 30

Newest Most relevant

763 papers this month