Imagen de Portada

PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chi, Cheng, Wang, Xianqi, Luo, Hongcheng, Tu, Mingfei, Xu, Gangwei, Zhang, Zehan, Wang, Bing, Chen, Guang, Ye, Hangjun, Peng, Sida, Yang, Xin, Sun, Haiyang
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Pixel-Perfect Visual Geometry Estimation
por: Xu, Gangwei, et al.
Publicado: (2026)

UFO: Unifying Feed-Forward and Optimization-based Methods for Large Driving Scene Modeling
por: Tan, Kaiyuan, et al.
Publicado: (2026)

Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers
por: Xu, Gangwei, et al.
Publicado: (2025)

DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images
por: Chen, Xiaoxue, et al.
Publicado: (2025)

FlowMamba: Learning Point Cloud Scene Flow with Global Motion Propagation
por: Lin, Min, et al.
Publicado: (2024)

PCSTracker: Long-Term Scene Flow Estimation for Point Cloud Sequences
por: Lin, Min, et al.
Publicado: (2026)

ExtraGS: Geometric-Aware Trajectory Extrapolation with Uncertainty-Guided Generative Priors
por: Tan, Kaiyuan, et al.
Publicado: (2025)

Mirage: One-Step Video Diffusion for Photorealistic and Coherent Asset Editing in Driving Scenes
por: Wang, Shuyun, et al.
Publicado: (2025)

Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching
por: Wang, Xianqi, et al.
Publicado: (2024)

Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency
por: Guo, Xiangyu, et al.
Publicado: (2025)

WorldSplat: Gaussian-Centric Feed-Forward 4D Scene Generation for Autonomous Driving
por: Zhu, Ziyue, et al.
Publicado: (2025)

Xiaomi Auto World Model: A Joint World Model Integrating Reconstruction and Generation for Autonomous Driving
por: Zhou, Lijun, et al.
Publicado: (2026)

BAT: Learning Event-based Optical Flow with Bidirectional Adaptive Temporal Correlation
por: Xu, Gangwei, et al.
Publicado: (2025)

ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
por: Li, Yongkang, et al.
Publicado: (2025)

Toward Physically Consistent Driving Video World Models under Challenging Trajectories
por: Zhou, Jiawei, et al.
Publicado: (2026)

ViSE: A Systematic Approach to Vision-Only Street-View Extrapolation
por: Tan, Kaiyuan, et al.
Publicado: (2025)

Bridging the Visual-to-Physical Gap: Physically Aligned Representations for Fall Risk Analysis
por: Zhang, Xianqi
Publicado: (2026)

Generalized Geometry Encoding Volume for Real-time Stereo Matching
por: Liu, Jiaxin, et al.
Publicado: (2025)

LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving
por: Luo, Yuechen, et al.
Publicado: (2026)

DriveLaW:Unifying Planning and Video Generation in a Latent Driving World
por: Xia, Tianze, et al.
Publicado: (2025)

Uni-Gaussians: Unifying Camera and Lidar Simulation with Gaussians for Dynamic Driving Scenarios
por: Yuan, Zikang, et al.
Publicado: (2025)

LVDrive: Latent Visual Representation Enhanced Vision-Language-Action Autonomous Driving Model
por: Mei, Xiaodong, et al.
Publicado: (2026)

IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching
por: Xu, Gangwei, et al.
Publicado: (2024)

UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving
por: Li, Yongkang, et al.
Publicado: (2026)

Reconstruction Matters: Learning Geometry-Aligned BEV Representation through 3D Gaussian Splatting
por: Lu, Yiren, et al.
Publicado: (2026)

PromptStereo: Zero-Shot Stereo Matching via Structure and Motion Prompts
por: Wang, Xianqi, et al.
Publicado: (2026)

StreetForward: Perceiving Dynamic Street with Feedforward Causal Attention
por: Yu, Zhongrui, et al.
Publicado: (2026)

Splat-SAP: Feed-Forward Gaussian Splatting for Human-Centered Scene with Scale-Aware Point Map Reconstruction
por: Zhou, Boyao, et al.
Publicado: (2025)

VGGDrive: Empowering Vision-Language Models with Cross-View Geometric Grounding for Autonomous Driving
por: Wang, Jie, et al.
Publicado: (2026)

DriveFine: Refining-Augmented Masked Diffusion VLA for Precise and Robust Driving
por: Dang, Chenxu, et al.
Publicado: (2026)

HDRFlow: Real-Time HDR Video Reconstruction with Large Motions
por: Xu, Gangwei, et al.
Publicado: (2024)

MeanFuser: Fast One-Step Multi-Modal Trajectory Generation and Adaptive Reconstruction via MeanFlow for End-to-End Autonomous Driving
por: Wang, Junli, et al.
Publicado: (2026)

DriveMRP: Enhancing Vision-Language Models with Synthetic Motion Data for Motion Risk Prediction
por: Hou, Zhiyi, et al.
Publicado: (2025)

FRUC: Feedforward Dynamic Scene Reconstruction from Uncalibrated Collaborative Driving Views
por: Tao, Yihang, et al.
Publicado: (2026)

Fast Point‐To‐Point Transportation of the Portal Crane via Double‐Input Inversion‐Based Feedforward and Feedback Control
por: Yongli Zhang, et al.
Publicado: (2025)

Hypergraph Representation via Axis-Aligned Point-Subspace Cover
por: Firman, Oksana, et al.
Publicado: (2021)

BANet: Bilateral Aggregation Network for Mobile Stereo Matching
por: Xu, Gangwei, et al.
Publicado: (2025)

Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks
por: Zeng, Kai, et al.
Publicado: (2025)

ReconDrive: Fast Feed-Forward 4D Gaussian Splatting for Autonomous Driving Scene Reconstruction
por: Yu, Haibao, et al.
Publicado: (2026)

On-the-fly Point Feature Representation for Point Clouds Analysis
por: Wang, Jiangyi, et al.
Publicado: (2024)