arXiv AI
Jun 19
DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis
arXiv:2604. 13416v2 Announce Type: replace-cross Abstract: Advances in radiance fields have enabled photorealistic novel view synthesis.
Attention-DP3: Spatially Object-aware 3D Diffusion Policy via Geometry-aligned Attentional Conditioning
Related stories
arXiv Machine Learning
Sep 10
CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs
arXiv:2609.08345v1 Announce Type: cross Abstract: Representing a 3D scene as multi-view images allows 2D VLMs to reason in 3D by reusing priors from pre-training, sidestepping the scarcity of annotat...
arXiv AI
Jul 29
SAM3D-Guided Object-Centric Representation Alignment for Vision-Language-Action Models
arXiv:2607. 25912v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have shown strong potential for general robot manipulation, but most existing models rely on 2D visual-language backbones and lack fine-grained 3D understanding of target objects, especially under occlusion, pose variation, scale changes, and precise spatial interaction.
arXiv Computer Vision
22h ago
GAPrompt++: Multi-Granular Geometry-Aware Point Cloud Prompt for 3D Vision Model
arXiv:2609.19716v1 Announce Type: new Abstract: Pre-trained 3D vision models have substantially advanced point cloud analysis, yet adapting them to downstream tasks via full fine-tuning is computatio...
arXiv Computer Vision
Aug 31
Video Generative Models as Geometry Learner
The paper introduces GeoNeXt, a framework that repurposes pretrained video generative models for geometry estimation by framing it as a next‑frame prediction task. Unlike prior methods that either train separate depth/normal models or fine‑tune image diffusion backbones, GeoNeXt jointly models images and geometric targets, leveraging the structured knowledge of video models for more data‑efficient learning. Experiments show zero‑shot monocular depth and surface normal estimation that outperforms existing generative approaches and rivals discriminative state‑of‑the‑art methods while using far less training data.
arXiv AI
Aug 25
PEAfowl: Perception-Enhanced Multi-View Vision-Language-Action for Bimanual Manipulation
arXiv:2601.17885v2 Announce Type: replace-cross Abstract: Bimanual manipulation in cluttered scenes requires policies that remain stable under occlusions, viewpoint changes and scene variations. Exis...
arXiv AI
Jun 29
S$^2$-VLA: State-Space Guided Vision-Language-Action Models for Long-Horizon Manipulation
arXiv:2606. 27872v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated strong capabilities in robotic manipulation, but their performance degrades significantly in long-horizon tasks due to cumulative error propagation.
arXiv AI
Jul 1
PruneGround: Plug-and-play Spatial Pruning for 3D Visual Grounding
arXiv:2606. 31148v1 Announce Type: cross Abstract: 3D Visual Grounding (3DVG) aims to localize target objects in 3D scenes given natural language descriptions.
arXiv Computer Vision
22h ago
SenseFuse: Label-Free Fusion of Image and Shape Encoders for Open-Vocabulary 3D Instance Segmentation
SenseFuse introduces a label‑free fusion approach that balances 2D image and 3D shape encoders for open‑vocabulary 3D instance segmentation. By selecting a scene‑level fusion weight through an adaptive, sensitivity‑based mechanism, it improves mask labeling accuracy across multiple datasets, recovering up to 93% of the potential gain from an oracle weight. The method demonstrates that image and shape encoders have complementary failure patterns, leading to higher instance AP in most evaluated settings.
arXiv AI
Jun 2
Real2SAM2Real: Generative 3D Caches as Complementary Context for Video Diffusion
arXiv:2606. 00299v1 Announce Type: cross Abstract: While Video Diffusion Models (VDMs) excel at synthesizing high-fidelity videos, enabling precise camera and scene control remains challenging.
arXiv AI
Aug 18
GaussMemory: Task-Driven 3D Gaussian Scene Memory for Long-Horizon Robotic Manipulation
arXiv:2608. 14986v1 Announce Type: cross Abstract: Long-horizon robotic manipulation fundamentally relies on persistent spatial memory.
arXiv Computer Vision
Sep 1
ACE-Ego-Hand: Repurposing Video Diffusion Models for Occlusion-Robust Egocentric 3D Hand Motion Recovery
arXiv:2608.20308v2 Announce Type: replace Abstract: Egocentric video offers scalable manipulation data for embodied AI, yet recovering metric 3D hand trajectories remains challenging due to severe ob...