NeuWorld uses a transformer VAE to learn compact Neural Implicit Scenes from sparse posed frames and a diffusion transformer to evolve them conditioned on camera trajectories for consistent interactive exploration.
More: 3d visual geometry reconstruction meets mixture-of-experts
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 5years
2026 5roles
background 1polarities
background 1representative citing papers
One transformer, trained with random-sized temporal attention chunks, unifies offline, streaming, and long-video depth, normal, and point-map estimation and reports new best numbers on five public benchmarks.
The paper proposes a problem-driven taxonomy for feed-forward 3D scene modeling that groups methods by five core challenges: feature enhancement, geometry awareness, model efficiency, augmentation strategies, and temporal-aware modeling.
A 14B-parameter mixture-of-experts world model is distilled to a four-step autoregressive generator and claimed to deliver camera-controllable video at up to 50 FPS on NPUs with 30-50% of prior inference cost.
LDCM achieves state-of-the-art metric depth completion from sparse observations by combining foundation-model initialization with a point-map regression head that removes the need for camera intrinsics.
citing papers explorer
-
Walking in the Implicit: Interactive World Exploration via Neural Scene Representation
NeuWorld uses a transformer VAE to learn compact Neural Implicit Scenes from sparse posed frames and a diffusion transformer to evolve them conditioned on camera trajectories for consistent interactive exploration.
-
Towards Consistent Video Geometry Estimation
One transformer, trained with random-sized temporal attention chunks, unifies offline, streaming, and long-video depth, normal, and point-map estimation and reports new best numbers on five public benchmarks.
-
Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective
The paper proposes a problem-driven taxonomy for feed-forward 3D scene modeling that groups methods by five core challenges: feature enhancement, geometry awareness, model efficiency, augmentation strategies, and temporal-aware modeling.
-
MoWorld: A Flash World Model
A 14B-parameter mixture-of-experts world model is distilled to a four-step autoregressive generator and claimed to deliver camera-controllable video at up to 50 FPS on NPUs with 30-50% of prior inference cost.
-
Large Depth Completion Model from Sparse Observations
LDCM achieves state-of-the-art metric depth completion from sparse observations by combining foundation-model initialization with a point-map regression head that removes the need for camera intrinsics.