arXiv Computer Vision
Causal Spatiotemporal State Evolution for Monocular 4D Reconstruction
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
Hugging Face Trending Papers
Jul 21
IGGT4D: Streaming 4D Instance-Grounded Geometry Transformer
Real-world spatial intelligence requires agents to understand scenes from continuous video streams, where objects move, persist, disappear, and reappear over time. While recent spatial foundation models have enabled generalizable feed-forward 3D reconstruction, most streaming methods remain geometry-centric and lack temporally consistent object-level understanding.
arXiv Computer Vision
Oct 7
ChronoWorld: Camera-Controlled Consistent 4D World Generation via Spatiotemporal Cues and Geometric Reflections
arXiv:2610.06687v2 Announce Type: replace Abstract: While existing camera-controllable video generation models can produce visually compelling sequences, preserving intrinsic 4D spatiotemporal cohere...
arXiv Computer Vision
Aug 27
4DStreamCtrl: Interactive Video Generation with Online 4D Control
The paper introduces 4DStreamCtrl, a system that unifies camera motion, object trajectories, and depth into a single 3D point‑track representation, enabling joint control, depth editing, and motion transfer in a single forward pass. By mining in‑the‑wild video for 3D motion supervision and encoding it with a lightweight Geometric Motion Head, the authors train a causal streaming student that can generate arbitrarily long videos in just four denoising steps, achieving 20 FPS on a single high‑end GPU for 480p video. This approach outperforms prior camera‑only, 2D, and offline‑3D methods in motion‑control precision while maintaining temporal coherence over hundreds of frames, thereby enabling interactive 4D‑controllable streaming generation for the first time.
arXiv AI
4d ago
RayCo4D: Ray-Conditioned Continuous Motion Model for Monocular 4D Dynamic Reconstruction
arXiv:2610.28351v1 Announce Type: cross Abstract: Reconstructing dynamic 3D scenes from monocular video requires inferring motion from noisy and intermittently visible observations. Long-range tracks...
arXiv Computer Vision
4d ago
PURE: Refining Feed-forward 3D Reconstruction with Unlabeled Post-training
PURE is an unlabeled post‑training refinement framework that enhances feed‑forward 3D reconstruction models by improving depth and camera estimation without ground‑truth supervision. It distills structural knowledge from state‑of‑the‑art 2D priors into 4D architectures, using relative depth constraints, affine‑invariant geometry distillation, and pose refinement via feature correspondences. Experiments on synthetic and real‑world dynamic benchmarks show consistent improvements across multiple state‑of‑the‑art models, effectively mitigating domain shifts and unlocking their architectural limits in challenging in‑the‑wild scenes.
arXiv Computer Vision
2d ago
WorldForge V2: Eliciting Camera-Trajectory Alignment in Video Diffusion Models
WorldForge V2 introduces a training‑free guidance framework that refines video diffusion outputs along a target camera path using warped references and optical‑flow‑identified latent channels for selective guidance. It employs a dual‑path strategy to correct artifacts, a v‑cache to reduce refinement cost, and Trajectory LoRA adapters trained in two stages to focus on trajectory‑responsive network blocks. The approach achieves state‑of‑the‑art generation quality and trajectory accuracy with minimal training data, enabling reliable camera control across unseen scenes.