10 papers
RegVGGT: Sustainable Visual Geometry Grounding for Streaming via Regulated Memory
Hongbo Mao, Junjun Jiang, Youyu Chen +3
3D reconstruction from a lengthy video stream input poses a dilemma for feed-forward reconstruction models (FFRMs), that a whole-stream inference context cannot be retained under l…
Tri-DehazeGS: Scene--Medium Decoupled Gaussian Splatting with Transmittance-Aware Optimization
Kui Jiang, Yang Gu, Jiacheng Liu +3
Recovering clean 3D scenes from hazy multi-view images is challenging because haze attenuates scene radiance and introduces atmospheric scattering. Recent scattering-aware Gaussian…
CoordRefer: Coordinate-Aware 3D Visual Grounding from Multiview Images
Haijie Li, Jiaxin Zhang, Dave Zhenyu Chen +3
Multiview image-based 3D visual grounding predicts a coordinate frame to define a coordinate system and then regresses a 3D bounding box for localization. However, existing methods…
AsySplat: Efficient Asymmetric 3D Gaussian Splatting for Long-Sequence Scene Modeling
Yingji Zhong, Dave Zhenyu Chen, Fuzhao Ou +4
Recent generalizable 3D Gaussian Splatting models have advanced long-sequence novel view synthesis (NVS), but at the cost of substantial redundant computation. We identify that the…
Reliev3R: Relieving Feed-forward Reconstruction from Multi-View Geometric Annotations
Youyu Chen, Junjun Jiang, Yueru Luo +4
With recent advances, Feed-forward Reconstruction Models (FFRMs) have demonstrated great potential in reconstruction quality and adaptiveness to multiple downstream tasks. However,…
GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models
Jiaxin Zhang, Junjun Jiang, Haijie Li +3
Multimodal Large Language Models (MLLMs) demonstrate exceptional semantic reasoning but struggle with 3D spatial perception when restricted to pure RGB inputs. Despite leveraging i…
Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting
Kangjie Chen, Yingji Zhong, Zhihao Li +4
3D Gaussian Splatting (3DGS) has demonstrated impressive performance in novel view synthesis under dense-view settings. However, in sparse-view scenarios, despite the realistic ren…
COB-GS: Clear Object Boundaries in 3DGS Segmentation Based on Boundary-Adaptive Gaussian Splitting
Jiaxin Zhang, Junjun Jiang, Youyu Chen +2
Accurate object segmentation is crucial for high-quality scene understanding in the 3D vision domain. However, 3D segmentation based on 3D Gaussian Splatting (3DGS) struggles with…
DashGaussian: Optimizing 3D Gaussian Splatting in 200 Seconds
Youyu Chen, Junjun Jiang, Kui Jiang +4
3D Gaussian Splatting (3DGS) renders pixels by rasterizing Gaussian primitives, where the rendering resolution and the primitive number, concluded as the optimization complexity, d…
FUSE: Label-Free Image-Event Joint Monocular Depth Estimation via Frequency-Decoupled Alignment and Degradation-Robust Fusion
Pihai Sun, Junjun Jiang, Yuanqi Yao +4
Image-event joint depth estimation methods leverage complementary modalities for robust perception, yet face challenges in generalizability stemming from two factors: 1) limited an…