arXiv:2609.01252v1 Announce Type: new Abstract: In camera-controlled video generation, geometry-aware positional encodings condition tokens on camera extrinsics and per-token viewing rays. Existing s...
arXiv:2601. 15275v3 Announce Type: replace-cross Abstract: We study positional encodings for multi-view transformers that process tokens from a set of posed input images, and seek a mechanism that encodes patches uniquely, allows SE(3)-invariant attention with multi-frequency similarity, and can adapt to the geometry of the underlying 3D scene.
We study relative position encoding for multi-view vision Transformers under camera heterogeneity, including varying fields of view (FoVs) or projection models. Existing rotary relative position encod...
The paper introduces G-ray, a ray-level relative position encoding for multi-view vision Transformers that remains consistent across different camera projections. By parameterizing rotary phases with camera-local ray angles, G-ray achieves projection-invariant positional consistency and can be integrated with existing encodings without extra learned parameters. Experiments on 3D reconstruction and novel-view synthesis benchmarks show that G-ray improves performance, notably reducing mean pointmap relative error by 45.8% over MapAnything.
MUGEN is a large‑scale real‑world dataset of over 1,300 hours of 4K panoramic videos with rich semantic and geometric annotations, designed to support interactive 360° world exploration. Wan360 is a camera‑controllable panoramic video generation model built on MUGEN, featuring ERP‑aware components (periodic longitude RoPE, ERP‑aware padding, random roll yaw) and a panoramic Plücker embedding for camera motion. Together, they address gaps in data and model support for immersive, temporally coherent 360° video generation along user‑specified camera trajectories.
The paper introduces CamTrol++, a training‑free method that stabilizes camera‑controlled novel view synthesis from a single image by decomposing large camera motions into small autoregressive steps, thereby limiting per‑step distortion and error accumulation. It also incorporates geometry‑constrained spatial attention, low‑frequency appearance anchoring, and a registration‑free warping pipeline to further enhance stability. Experiments on RealEstate10K and MegaScene demonstrate improved temporal and geometric consistency, better downstream 3D reconstruction quality, and higher generation efficiency, even for long 56‑frame sequences and under depth corruption.
arXiv:2607. 00832v1 Announce Type: cross Abstract: A single panorama captures the full visual sphere from one camera center, yet confines users to looking around in place without enabling true scene exploration.
RoGe is a new end‑to‑end framework for novel view synthesis that jointly learns an implicit 3D scene representation and a video diffusion model. It eliminates the need for explicit 3D intermediates by querying the implicit scene with camera rays to produce geometric features that condition the diffusion model. Experiments on DL3DV show that RoGe surpasses reconstruction‑based, generation‑based, and hybrid baselines in image quality and temporal consistency, and ablations confirm the benefits of ray‑queried features and joint training.
Synthesizing a novel-view video from a monocular reference video along a target camera trajectory requires both geometric consistency and motion fidelity with respect to the reference video. Existing methods based on explicit 3D representations are limited by the accuracy of off-the-shelf reconstruction modules, which often produce inaccurate geometry for dynamic objects in monocular videos.
arXiv:2512. 16919v2 Announce Type: replace-cross Abstract: Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving.
World in World introduces a training‑free, inference‑time interface that transforms diverse control signals—such as source‑video observations, target‑view projections, geometry renderings, and retrieved states—into camera‑ and time‑labelled visual states. These states are processed by a frozen causal video model’s self‑attention, enabling tasks like camera‑controlled rerendering, long‑horizon revisiting, and human‑motion transfer without additional training. The method employs a correspondence router and evidence‑wise attention to align token identities and regulate auxiliary channel contributions during a single denoising pass.
The paper proposes a new sequence-to-sequence formulation for multi-view stereo (MVS) that jointly predicts 3D geometry for all input views using a global transformer architecture. It introduces ray‑map embeddings to inject camera parameters into image tokens and a unified global cost volume to capture 3D structure across all views. Experiments on public benchmarks demonstrate state‑of‑the‑art performance, outperforming both traditional MVS and feed‑forward reconstruction baselines.