9 papers
CodecArena: Codec Quality Assessment via Visual Reinforcement Learning
Jiaye Fu, Weiqi Li, Qiankun Gao +5
Video coding is advancing into the low and ultra-low bitrate regime, driven by end-to-end codecs that replace the hand-crafted pipeline with jointly optimized neural networks and g…
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…
Spark3R: Asymmetric Token Reduction Makes Fast Feed-Forward 3D Reconstruction
Zecheng Tang, Jiaye Fu, Qiankun Gao +5
Feed-forward 3D reconstruction models based on Vision Transformers can directly estimate scene geometry and camera poses from a small set of input images, but scaling them to video…
ReCon-GS: Continuum-Preserved Gaussian Streaming for Fast and Compact Reconstruction of Dynamic Scenes
Jiaye Fu, Qiankun Gao, Chengxiang Wen +4
Online free-viewpoint video (FVV) reconstruction is challenged by slow per-frame optimization, inconsistent motion estimation, and unsustainable storage demands. To address these c…
InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception
Haijie Li, Yanmin Wu, Jiarui Meng +4
3D scene understanding has become an essential area of research with applications in autonomous driving, robotics, and augmented reality. Recently, 3D Gaussian Splatting (3DGS) has…
HiCoM: Hierarchical Coherent Motion for Streamable Dynamic Scene with 3D Gaussian Splatting
Qiankun Gao, Jiarui Meng, Chengxiang Wen +2
The online reconstruction of dynamic scenes from multi-view streaming videos faces significant challenges in training, rendering and storage efficiency. Harnessing superior learnin…