TagSplat: Topology-Aware Gaussian Splatting for Dynamic Mesh Modeling and Tracking
Topology-consistent dynamic model sequences are essential for applications such as animation and model editing. However, existing 4D reconstruction methods face challenges in generating high-qualit...
ConceptPose: Training-Free Zero-Shot Object Pose Estimation using Concept Vectors
Object pose estimation is a fundamental task in computer vision and robotics, yet most methods require extensive, dataset-specific training. Concurrently, large-scale vision language models show re...
Dual Ascent Diffusion for Inverse Problems
Ill-posed inverse problems are fundamental in many domains, ranging from astrophysics to medical imaging. Emerging diffusion models provide a powerful prior for solving these problems. Existing max...
Generalizable Structure-Aware Keypoint Correspondence for Category-Unified 3D Single Object Tracking
3D single object tracking (SOT) in point clouds is essential for real-world 3D perception, yet it remains challenging due to data sparsity and large variations in scale and structure across diverse...
DirectFisheye-GS: Enabling Native Fisheye Input in Gaussian Splatting with Cross-View Joint Optimization
3D Gaussian Splatting (3DGS) has enabled efficient 3D scene reconstruction from everyday images with real-time, high-fidelity rendering, greatly advancing VR/AR applications. Fisheye cameras, with ...
Choreographing a World of Dynamic Objects
Dynamic objects in our physical 4D (3D + time) world are constantly evolving, deforming, and interacting with other objects, leading to diverse 4D scene dynamics. In this paper, we present a univer...
Spk2VidNet: A Hierarchical Recurrent Architecture for High-Fidelity Video Reconstruction from Long Spike-Camera Streams
Spike camera is a neuromorphic vision sensor with ultra-high temporal resolution, capable of capturing fast-moving scenes by firing a stream of binary spikes. However, its relatively low spatial re...
Continual Distillation of Teachers from Different Domains
Deep learning models continue to scale, with some requiring more storage than many large-scale datasets. Thus, we introduce a new paradigm: Continual Distillation (CD), where a student learns seque...
Beyond Euclidean Gossip: KL-Barycentric Consensus on Heterogeneous and Imbalanced Images
Fully decentralized deep learning removes global servers and ensures local data privacy. However, Euclidean consensus, averaging weights, gradients or momentum, may degrade under the situations wit...
HybridDriveVLA: Vision-Language-Action Model with Visual CoT reasoning and ToT Evaluation for Autonomous Driving
Vision-Language-Action (VLA) models are emerging as an important technology in autonomous driving, recognized for their sophisticated reasoning and interpretability. However, traditional VLA models...
GT-SVJ: Generative-Transformer-Based Self-Supervised Video Judge For Efficient Video Reward Modeling
Aligning video generative models with human preferences remains challenging: current approaches rely on Vision-Language Models (VLMs) for reward modeling, but these models struggle to capture subtl...
Catalyst4D: High-Fidelity 3D-to-4D Scene Editing via Dynamic Propagation
Recent advances in 3D scene editing using NeRF and 3DGS enable high-quality static scene editing. In contrast, dynamic scene editing remains challenging, as methods that directly extend 2D diffusio...
Cloning Deterministic Worlds: The Critical Role of Latent Geometry in Long-Horizon World Models
A world model is an internal model that simulates how the world evolves. Given past observations and actions, it predicts the future physical state of both the embodied agent and its environment. A...
CME-CAD: Heterogeneous Collaborative Multi-Expert Reinforcement Learning for CAD Code Generation
Computer-Aided Design (CAD) is essential in industrial design, but the complexity of traditional CAD modeling and workflows presents significant challenges for automating the generation of high-pre...
Unique Lives, Shared World: Learning from Single-Life Videos
We introduce the "single-life" learning paradigm, where we train a distinct vision model exclusively on egocentric videos captured by one individual. We leverage the multiple viewpoints naturally c...
UniComp: Rethinking Video Compression Through Informational Uniqueness
Distinct from attention-based compression methods, this paper presents an information uniqueness driven video compression framework, termed UniComp, which aims to maximize the information fidelity ...
AD-GBC: Anisotropic Granular-Ball Skip-Connection Refiner for UNet-Based Medical Image Segmentation
Prototype or region-attention modules have recently improved medical image segmentation but still suffer from two fundamental limitations: 1) they represent each semantic concept as a point or isot...
EcoSplat: Efficiency-controllable Feed-forward 3D Gaussian Splatting from Multi-view Images
Feed-forward 3D Gaussian Splatting (3DGS) enables efficient one-pass scene reconstruction, providing 3D representations for novel view synthesis without per-scene optimization. However, existing me...
PanoEnv: Exploring 3D Spatial Intelligence in Panoramic Environments with Reinforcement Learning
360deg panoramic images are increasingly used in VR, autonomous driving, and robotics for holistic scene understanding. However, current Vision-Language Models (VLMs) struggle with 3D spatial reaso...
AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend
We present AMB3R, a multi-view feed-forward model for metric-scale dense 3D reconstruction that addresses diverse 3D vision tasks. The key idea is to employ a sparse, yet compact, volumetric scene ...
