1 citations · 2 across the 46 of their papers we have counts for
15 papers · 1 filter
Semantics Disentanglement and Composition for Universal Image Coding with Efficiently LLM Reasoning and Generative Diffusion
Jinming Liu, Yuntao Wei, Junyan Lin +5
Learned image compression methods have shown impressive performance but are often highly specialized for either human perception or specific machine vision tasks. This specializati…
OccScene: Semantic Occupancy-based Cross-task Mutual Learning for 3D Scene Generation
Bohan Li, Xin Jin, Jianan Wang +8
Recent diffusion models have demonstrated remarkable performance in both 3D scene generation and perception tasks. Nevertheless, existing methods typically separate these two proce…
Hierarchical Context Alignment with Disentangled Geometric and Temporal Modeling for Semantic Occupancy Prediction
Bohan Li, Jiajun Deng, Yasheng Sun +3
Camera-based 3D Semantic Occupancy Prediction (SOP) is crucial for understanding complex 3D scenes from limited 2D image observations. Existing SOP methods typically aggregate cont…
UniScene: Unified Occupancy-centric Driving Scene Generation
Bohan Li, Jiazhe Guo, Hongsi Liu +14
Generating high-fidelity, controllable, and annotated training data is critical for autonomous driving. Existing methods typically generate a single data form directly from a coars…
MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotations
Liang Xu, Shaoyang Hua, Zili Lin +6
In this paper, we tackle the problem of how to build and benchmark a large motion model (LMM). The ultimate goal of LMM is to serve as a foundation model for versatile motion-relat…
Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation
Yunnan Wang, Ziqiang Li, Zequn Zhang +5
There has been exciting progress in generating images from natural language or layout conditions. However, these methods struggle to faithfully reproduce complex scenes due to the…
Tell Codec What Worth Compressing: Semantically Disentangled Image Coding for Machine with LMMs
Jinming Liu, Yuntao Wei, Junyan Lin +5
We present a new image compression paradigm to achieve ``intelligently coding for machine'' by cleverly leveraging the common sense of Large Multimodal Models (LMMs). We are motiva…
Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models
Baao Xie, Qiuyu Chen, Yunnan Wang +3
Disentangled representation learning (DRL) aims to identify and decompose underlying factors behind observations, thus facilitating data perception and generation. However, current…
Rate-Distortion-Cognition Controllable Versatile Neural Image Compression
Jinming Liu, Ruoyu Feng, Yunpeng Qi +4
Recently, the field of Image Coding for Machines (ICM) has garnered heightened interest and significant advances thanks to the rapid progress of learning-based techniques for image…
HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects
Xintao Lv, Liang Xu, Yichao Yan +8
Generating human-object interactions (HOIs) is critical with the tremendous advances of digital avatars. Existing datasets are typically limited to humans interacting with a single…
Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion
Bohan Li, Jiajun Deng, Wenyao Zhang +4
Camera-based 3D semantic scene completion (SSC) is pivotal for predicting complicated 3D layouts with limited 2D image observations. The existing mainstream solutions generally lev…
RLeXplore: Accelerating Research in Intrinsically-Motivated Reinforcement Learning
Mingqi Yuan, Roger Creus Castanyer, Bo Li +3
Extrinsic rewards can effectively guide reinforcement learning (RL) agents in specific tasks. However, extrinsic rewards frequently fall short in complex environments due to the si…
Hierarchical Procedural Framework for Low-latency Robot-Assisted Hand-Object Interaction
Mingqi Yuan, Huijiang Wang, Kai-Fung Chu +3
Advances in robotics have been driving the development of human-robot interaction (HRI) technologies. However, accurately perceiving human actions and achieving adaptive control re…
ReGenNet: Towards Human Action-Reaction Synthesis
Liang Xu, Yizhou Zhou, Yichao Yan +5
Humans constantly interact with their surrounding environments. Current human-centric generative models mainly focus on synthesizing humans plausibly interacting with static scenes…
Closed-Loop Unsupervised Representation Disentanglement with -VAE Distillation and Diffusion Probabilistic Feedback
Xin Jin, Bohan Li, BAAO Xie +5
Representation disentanglement may help AI fundamentally understand the real world and thus benefit both discrimination and generation tasks. It currently has at least three unreso…