6 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…
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…
Enhanced Template-based Intra Mode Derivation with Adaptive Block Vector Replacement
Jiaqi Zhang, Jiaye Fu, Chuanmin Jia +5
Intra prediction is a crucial component in traditional video coding frameworks, aiming to eliminate spatial redundancy within frames. In recent years, an increasing number of decod…
TinySplat: Feedforward Approach for Generating Compact 3D Scene Representation
Zetian Song, Jiaye Fu, Jiaqi Zhang +4
The recent development of feedforward 3D Gaussian Splatting (3DGS) presents a new paradigm to reconstruct 3D scenes. Using neural networks trained on large-scale multi-view dataset…
ProSplat: Improved Feed-Forward 3D Gaussian Splatting for Wide-Baseline Sparse Views
Xiaohan Lu, Jiaye Fu, Jiaqi Zhang +3
Feed-forward 3D Gaussian Splatting (3DGS) has recently demonstrated promising results for novel view synthesis (NVS) from sparse input views, particularly under narrow-baseline con…