Related papers: RLGF: Reinforcement Learning with Geometric Feedba…

Synthesizing high dynamic range (HDR) images from multiple low-dynamic range (LDR) exposures in dynamic scenes is challenging. There are two major problems caused by the large motions of foreground objects. One is the severe misalignment…

In this paper, we propose a 3D geometry-aware deformable Gaussian Splatting method for dynamic view synthesis. Existing neural radiance fields (NeRF) based solutions learn the deformation in an implicit manner, which cannot incorporate 3D…

High-level autonomous driving requires motion planners capable of modeling multimodal future uncertainties while remaining robust in closed-loop interactions. Although diffusion-based planners are effective at modeling complex trajectory…

Existing fine-grained image retrieval (FGIR) methods predominantly rely on supervision from predefined categories to learn discriminative representations for retrieving fine-grained objects. However, they inadvertently introduce…

Despite some successful applications of goal-driven navigation, existing deep reinforcement learning (DRL)-based approaches notoriously suffers from poor data efficiency issue. One of the reasons is that the goal information is decoupled…

This study introduces an enhanced approach to video super-resolution by extending ordinary Single-Image Super-Resolution (SISR) Super-Resolution Generative Adversarial Network (SRGAN) structure to handle spatio-temporal data. While SRGAN…

Pre-trained Latent Diffusion Models (LDMs) have recently shown strong perceptual priors for low-level vision tasks, making them a promising direction for multi-exposure High Dynamic Range (HDR) reconstruction. However, directly applying…

GeRaF is the first method to use neural implicit learning for near-range 3D geometry reconstruction from radio frequency (RF) signals. Unlike RGB or LiDAR-based methods, RF sensing can see through occlusion but suffers from low resolution…

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a promising framework for improving reasoning abilities in Large Language Models (LLMs). However, policy optimized with binary verification prone to overlook…

4D automotive radar is indispensable for autonomous driving due to its low cost and robustness, yet its point cloud sparsity challenges 3D object detection. Existing 4D radar-camera fusion methods focus on complex fusion strategies, trading…

Recent advances in 3D scene generation produce visually appealing output, but current representations hinder artists' workflows that require modifiable 3D textured mesh scenes for visual effects and game development. Despite significant…

Multimodal Large Language Models (MLLMs) demonstrate exceptional semantic reasoning but struggle with 3D spatial perception when restricted to pure RGB inputs. Despite leveraging implicit geometric priors from 3D reconstruction models,…

Recent advances in diffusion-based and autoregressive video generation models have achieved remarkable visual realism. However, these models typically lack accurate physical alignment, failing to replicate real-world dynamics in object…

The generation of high-quality 3D car assets is essential for various applications, including video games, autonomous driving, and virtual reality. Current 3D generation methods utilizing NeRF or 3D-GS as representations for 3D objects,…

Multimodal Large Language Models (MLLMs) struggle with complex geometric reasoning, largely because "black box" outcome-based supervision fails to distinguish between lucky guesses and rigorous deduction. To address this, we introduce a…

By combining natural language understanding, generation capabilities, and breadth of knowledge of large language models with image perception, recent large vision language models (LVLMs) have shown unprecedented visual reasoning…

High-fidelity 3D video reconstruction is essential for enabling real-time rendering of dynamic scenes with realistic motion in virtual and augmented reality (VR/AR). The deformation field paradigm of 3D Gaussian splatting has achieved…

Addressing the critical need for robust safety in Large Language Models (LLMs), particularly against adversarial attacks and in-distribution errors, we introduce Reinforcement Learning with Backtracking Feedback (RLBF). This framework…

Dynamic objects have a significant impact on the robot's perception of the environment which degrades the performance of essential tasks such as localization and mapping. In this work, we address this problem by synthesizing plausible…

Real-time traffic prediction is critical for managing transportation systems during hurricane evacuations. Although data-driven graph-learning models have demonstrated strong capabilities in capturing the complex spatiotemporal dynamics of…