Papers

Field

Top tools here

Open problems in 3D scene

3D consistency in generated scenes3 papers raise it · 3 address it
Generated videos and scenes often lack geometric and multi-view consistency, breaking realism for interactive or dynamic use.
- OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphsraises · addresses
- Orbia: Do Generated Videos Form a Consistent 3D World?raises · addresses
- GeoFix: Geometry Fixing for 4D Consistent Generationraises · addresses
High-quality novel view synthesis under large viewpoint changes3 papers raise it · 3 address it
Feed-forward methods struggle to render high-quality views when camera poses differ greatly from training inputs.
- 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
Dense correspondence matching without spatio-temporal priors1 paper raises it · 1 addresses it
Existing correspondence methods fail when transformations break physical continuity, limiting applications like image editing.
- Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matchingraises · addresses
Physics and geometry coherence in 3D scene generation1 paper raises it · 1 addresses it
Generated 3D scenes often lack fine-grained spatial and physical plausibility between interacting objects.
- Tetris3D: 3D Scene Generation With Objects That Fit Togetherraises · addresses
Metric distance estimation in 3D reconstruction1 paper raises it · 1 addresses it
Current benchmarks do not directly evaluate point-to-point distance accuracy, a fundamental requirement for many 3D tasks.
- Pumpire: Unified Benchmark for Metric Distance Estimationraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Topics in this field

3d scene · 3d reconstruction · depth estimation268 papers43 this week
gaussian splatting 3dgs · 3d gaussian splatting · feed forward 3d212 papers37 this week
small target detection · infrared small target · target detection122 papers26 this week
remote sensing · satellite imagery · earth observation133 papers25 this week
point cloud registration · 3d point clouds · point cloud72 papers18 this week
camera lidar · 3d object detection · point clouds96 papers14 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 30
Lens Flare Removal and Reconstruction
Tarun Yenamandra, Jonathon Luiten, Daniel Cremers, Nathan Matsuda
The presence of lens flares in images can significantly reduce the quality of downstream application results for tasks such as 3D scene reconstruction. This is because lens flares are a property of the camera imaging system, and not a part of the underlying scene being modeled. There are previous methods that tackle the removal of small flares focused around a light source. However, existing methods struggle with large flares, such as those that fill the entire image. In this work, we compile a novel dataset for large-flare removal, combining publicly available real-world data with a procedural generation pipeline. We fine-tune a diffusion-based model on our dataset to remove complex, large lens flares. On the other hand, lens flares remain effective artistic tools, widely used in the media. While there are ways to simulate 2D flares, representing and reconstructing lens flares consistently across multiple views has not yet been explored. To achieve this, we introduce a flare representation model that leverages the symmetry of lens flares about the camera's principal point. We propose a computational pipeline to jointly optimize this flare model and a Gaussian splatting model…
PDF arXiv
arXiv cs.CVSep 30
Front-to-Back: Benchmarking Vision-Language Models for Asymmetric Cross-View Vehicle Re-Identification
Moseli Mots'oehli, Thulani Babeli
Matching the same vehicle across front and rear cameras is difficult because the cameras do not share a view and the vehicle's appearance changes substantially. We introduce Front2Back-ReID, a benchmark of 500 manually verified vehicle handovers from 20 recording sequences in South Africa. Each example asks a model to match a vehicle highlighted in a front-camera image to the same vehicle among at least three candidates in a later rear-camera image. We evaluate seven zero-shot vision-language models, four image-retrieval baselines, and 25 human participants. Models are tested using full front RGB images, cropped target vehicles, and binary silhouettes. The strongest VLM achieved 76.6 percent Rank-1 accuracy on target crops, compared with 74.0 percent for the frozen SigLIP2 baseline; this difference was not statistically clear. Human participants achieved 94.0 percent accuracy with full images and 92.2 percent with target crops. Under our evaluation setup, enabling reasoning improved accuracy across all three input conditions for every model evaluated in both modes. We also found that VLMs generally performed worse on full scenes than on target crops. These results show that…
PDF arXiv
arXiv cs.CVSep 30
DensePed-Lite: Quality-Aware Adaptive Detection for Dense Pedestrians under Occlusion
ZiAn Wang, MingZhe Liu, Chaoyi Guo, ChangChun Li, Fangming Gu
Pedestrian detection plays a crucial role in computer vision with applications in autonomous driving, surveillance, and public safety. However, real-world dense scenes bring severe challenges, including heavy occlusion, drastic scale variations, and strict real-time requirements. Existing lightweight detectors struggle to balance accuracy and efficiency while often neglecting quality-aware feature modeling and consistency between classification and localization, leading to unstable performance under crowded conditions. To address these issues, we propose DensePed-Lite, a unified framework built on a single principle: under occlusion the network should adapt its behavior to the quality of what it observes rather than assume complete information. This principle is realized at three points where occlusion does the most damage: unreliable confidence scoring (UQE), fragmented spatial coverage (MPSC), and incoherent multi-scale fusion (CTDM). The three mechanisms reinforce one another instead of acting in isolation, all without significantly increasing complexity. Experiments on CityPersons and CrowdHuman validate that DensePed-Lite achieves a superior accuracy-efficiency trade-off…
PDF arXiv
arXiv cs.CVSep 30
COBICount: Separating Object and Background Responses for Remote Sensing Object Counting Without Training on Target Data
Junjing Zheng, Zhiyi Zhou, Ningrui Yang, Hongying Meng
Remote sensing object counting estimates how many buildings, vehicles, or ships appear in overhead images. Most supervised counters predict a density map, whose sum gives the object count, and assume similar categories, sizes, and backgrounds. Applying them across regions, sensors, or categories often requires target data or further training, which may be costly or unavailable. We study source-only counting. Training for the counting task and model selection use one group of images that shares an object category and similar imaging conditions, with one point marking each object. Target images and information remain unavailable until the model is fixed. This reduces data preparation but makes transfer harder. A model trained on one source may place high density values, called responses, on real objects and repeated background structures. Road edges, parking grids, roof boundaries, and water boundaries may then be counted as objects, creating candidate origin ambiguity. COBICount separates response generation, acceptance, and background suppression. Candidate Evidence (CE) generates possible responses. Candidate Acceptance (CA) keeps compact responses centered on objects. Bias…
PDF arXiv
arXiv cs.CVSep 30
Emergent Multi-View Geometry Through Self-Distillation
David Nordström, Thibaut Loiseau, Vincent Lepetit, Michael Felsberg, Guillaume Bourmaud +1
Over a century ago, Henri Poincaré argued that a motionless observer cannot acquire the notion of space. Yet, most visual representation learning methods operate on individual images, while those that leverage multiple views rely on RGB reconstruction, entangling geometry with appearance. We propose Poincar3, a self-supervised method that learns representations from multiple views through self-distillation instead of RGB reconstruction. We combine masked patch and image-level distillation with a teacher that observes additional views, enabling training from scratch without explicit 3D supervision. Poincar3 outperforms both previous single and multi-view self-supervised approaches such as DINOv3, MuM, and Muskie on correspondence estimation, camera pose estimation, and 3D reconstruction. Using a lightweight Poincaré adapter, we also find that our learned features encode camera motion more accurately than existing self-supervised representations.
PDF arXiv
arXiv cs.CVSep 30
GRC-Pose: Generation-Reconstruction Correspondence for Prior-Free 6D Object Pose Tracking
Shiyang Liu, Weiquan Lin, Luping Xiao, Jiadong Tang, Yi Yang +2
Prior-free 6D object pose tracking seeks to recover the trajectory of an unseen object from a single RGB video without object-specific CAD models, posed reference images, or pose annotations. Geometric foundation models provide complementary object-centric and scene-centric cues, yet SAM3D CAD is indexed by an arbitrary object-local surface parameterization, whereas reconstructed evidence is expressed in a sequence-specific world frame with partial surface coverage. To exploit this complementarity, we formulate tracking as generation-reconstruction correspondence and introduce GRC-Pose, a correspondence-based framework that combines learned correspondence prediction with robust pose estimation. Concretely, GeoCorr-Matcher estimates weighted object-scene correspondences and per-match uncertainty for each pose candidate. FGH-Solver integrates these matches through multiple robust geometric estimators and sequence-level posterior inference, while a posterior-gated memory retains only inlier-supported observations through occlusion and viewpoint change. Extensive evaluation shows that with SAM3D CAD, GRC-Pose achieves state-of-the-art Average Recall and motion retention on HOT3D,…
PDF arXiv

Papers

Topics in this field

3d scene · 3d reconstruction · depth estimation268 papers43 this week
gaussian splatting 3dgs · 3d gaussian splatting · feed forward 3d212 papers37 this week
small target detection · infrared small target · target detection122 papers26 this week
remote sensing · satellite imagery · earth observation133 papers25 this week
point cloud registration · 3d point clouds · point cloud72 papers18 this week
camera lidar · 3d object detection · point clouds96 papers14 this week

Active contributors · 90 days

Activity · 12 weeks

Open problems in 3D scene

3D consistency in generated scenes3 papers raise it · 3 address it
Generated videos and scenes often lack geometric and multi-view consistency, breaking realism for interactive or dynamic use.
- OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphsraises · addresses
- Orbia: Do Generated Videos Form a Consistent 3D World?raises · addresses
- GeoFix: Geometry Fixing for 4D Consistent Generationraises · addresses
High-quality novel view synthesis under large viewpoint changes3 papers raise it · 3 address it
Feed-forward methods struggle to render high-quality views when camera poses differ greatly from training inputs.
- 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
Dense correspondence matching without spatio-temporal priors1 paper raises it · 1 addresses it
Existing correspondence methods fail when transformations break physical continuity, limiting applications like image editing.
- Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matchingraises · addresses
Physics and geometry coherence in 3D scene generation1 paper raises it · 1 addresses it
Generated 3D scenes often lack fine-grained spatial and physical plausibility between interacting objects.
- Tetris3D: 3D Scene Generation With Objects That Fit Togetherraises · addresses
Metric distance estimation in 3D reconstruction1 paper raises it · 1 addresses it
Current benchmarks do not directly evaluate point-to-point distance accuracy, a fundamental requirement for many 3D tasks.
- Pumpire: Unified Benchmark for Metric Distance Estimationraises · addresses

Named by an AI from these papers' abstracts.

Recent papers

All papers in Research

arXiv cs.CVSep 30
Lens Flare Removal and Reconstruction
Tarun Yenamandra, Jonathon Luiten, Daniel Cremers, Nathan Matsuda
The presence of lens flares in images can significantly reduce the quality of downstream application results for tasks such as 3D scene reconstruction. This is because lens flares are a property of the camera imaging system, and not a part of the underlying scene being modeled. There are previous methods that tackle the removal of small flares focused around a light source. However, existing methods struggle with large flares, such as those that fill the entire image. In this work, we compile a novel dataset for large-flare removal, combining publicly available real-world data with a procedural generation pipeline. We fine-tune a diffusion-based model on our dataset to remove complex, large lens flares. On the other hand, lens flares remain effective artistic tools, widely used in the media. While there are ways to simulate 2D flares, representing and reconstructing lens flares consistently across multiple views has not yet been explored. To achieve this, we introduce a flare representation model that leverages the symmetry of lens flares about the camera's principal point. We propose a computational pipeline to jointly optimize this flare model and a Gaussian splatting model…
PDF arXiv
arXiv cs.CVSep 30
Front-to-Back: Benchmarking Vision-Language Models for Asymmetric Cross-View Vehicle Re-Identification
Moseli Mots'oehli, Thulani Babeli
Matching the same vehicle across front and rear cameras is difficult because the cameras do not share a view and the vehicle's appearance changes substantially. We introduce Front2Back-ReID, a benchmark of 500 manually verified vehicle handovers from 20 recording sequences in South Africa. Each example asks a model to match a vehicle highlighted in a front-camera image to the same vehicle among at least three candidates in a later rear-camera image. We evaluate seven zero-shot vision-language models, four image-retrieval baselines, and 25 human participants. Models are tested using full front RGB images, cropped target vehicles, and binary silhouettes. The strongest VLM achieved 76.6 percent Rank-1 accuracy on target crops, compared with 74.0 percent for the frozen SigLIP2 baseline; this difference was not statistically clear. Human participants achieved 94.0 percent accuracy with full images and 92.2 percent with target crops. Under our evaluation setup, enabling reasoning improved accuracy across all three input conditions for every model evaluated in both modes. We also found that VLMs generally performed worse on full scenes than on target crops. These results show that…
PDF arXiv
arXiv cs.CVSep 30
DensePed-Lite: Quality-Aware Adaptive Detection for Dense Pedestrians under Occlusion
ZiAn Wang, MingZhe Liu, Chaoyi Guo, ChangChun Li, Fangming Gu
Pedestrian detection plays a crucial role in computer vision with applications in autonomous driving, surveillance, and public safety. However, real-world dense scenes bring severe challenges, including heavy occlusion, drastic scale variations, and strict real-time requirements. Existing lightweight detectors struggle to balance accuracy and efficiency while often neglecting quality-aware feature modeling and consistency between classification and localization, leading to unstable performance under crowded conditions. To address these issues, we propose DensePed-Lite, a unified framework built on a single principle: under occlusion the network should adapt its behavior to the quality of what it observes rather than assume complete information. This principle is realized at three points where occlusion does the most damage: unreliable confidence scoring (UQE), fragmented spatial coverage (MPSC), and incoherent multi-scale fusion (CTDM). The three mechanisms reinforce one another instead of acting in isolation, all without significantly increasing complexity. Experiments on CityPersons and CrowdHuman validate that DensePed-Lite achieves a superior accuracy-efficiency trade-off…
PDF arXiv
arXiv cs.CVSep 30
COBICount: Separating Object and Background Responses for Remote Sensing Object Counting Without Training on Target Data
Junjing Zheng, Zhiyi Zhou, Ningrui Yang, Hongying Meng
Remote sensing object counting estimates how many buildings, vehicles, or ships appear in overhead images. Most supervised counters predict a density map, whose sum gives the object count, and assume similar categories, sizes, and backgrounds. Applying them across regions, sensors, or categories often requires target data or further training, which may be costly or unavailable. We study source-only counting. Training for the counting task and model selection use one group of images that shares an object category and similar imaging conditions, with one point marking each object. Target images and information remain unavailable until the model is fixed. This reduces data preparation but makes transfer harder. A model trained on one source may place high density values, called responses, on real objects and repeated background structures. Road edges, parking grids, roof boundaries, and water boundaries may then be counted as objects, creating candidate origin ambiguity. COBICount separates response generation, acceptance, and background suppression. Candidate Evidence (CE) generates possible responses. Candidate Acceptance (CA) keeps compact responses centered on objects. Bias…
PDF arXiv
arXiv cs.CVSep 30
Emergent Multi-View Geometry Through Self-Distillation
David Nordström, Thibaut Loiseau, Vincent Lepetit, Michael Felsberg, Guillaume Bourmaud +1
Over a century ago, Henri Poincaré argued that a motionless observer cannot acquire the notion of space. Yet, most visual representation learning methods operate on individual images, while those that leverage multiple views rely on RGB reconstruction, entangling geometry with appearance. We propose Poincar3, a self-supervised method that learns representations from multiple views through self-distillation instead of RGB reconstruction. We combine masked patch and image-level distillation with a teacher that observes additional views, enabling training from scratch without explicit 3D supervision. Poincar3 outperforms both previous single and multi-view self-supervised approaches such as DINOv3, MuM, and Muskie on correspondence estimation, camera pose estimation, and 3D reconstruction. Using a lightweight Poincaré adapter, we also find that our learned features encode camera motion more accurately than existing self-supervised representations.
PDF arXiv
arXiv cs.CVSep 30
GRC-Pose: Generation-Reconstruction Correspondence for Prior-Free 6D Object Pose Tracking
Shiyang Liu, Weiquan Lin, Luping Xiao, Jiadong Tang, Yi Yang +2
Prior-free 6D object pose tracking seeks to recover the trajectory of an unseen object from a single RGB video without object-specific CAD models, posed reference images, or pose annotations. Geometric foundation models provide complementary object-centric and scene-centric cues, yet SAM3D CAD is indexed by an arbitrary object-local surface parameterization, whereas reconstructed evidence is expressed in a sequence-specific world frame with partial surface coverage. To exploit this complementarity, we formulate tracking as generation-reconstruction correspondence and introduce GRC-Pose, a correspondence-based framework that combines learned correspondence prediction with robust pose estimation. Concretely, GeoCorr-Matcher estimates weighted object-scene correspondences and per-match uncertainty for each pose candidate. FGH-Solver integrates these matches through multiple robust geometric estimators and sequence-level posterior inference, while a posterior-gated memory retains only inlier-supported observations through occlusion and viewpoint change. Extensive evaluation shows that with SAM3D CAD, GRC-Pose achieves state-of-the-art Average Recall and motion retention on HOT3D,…
PDF arXiv

Fields · AI · updated 44m ago

3D scene

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

163papers this week−13.3% vs last week

All papers · 903 With code · 28

Newest Most relevant

806 papers this month