The paper introduces a framework for generating multi‑view images of a person within a natural scene, addressing the scarcity of paired multi‑view datasets for human subjects. It evaluates existing diffusion‑based image‑editing models and finds they often hallucinate head‑turn angles, leading to inconsistent backgrounds. To overcome this, the authors propose the Head Scene Rotation Difference (HSRD) metric, which separates camera movement from head pose changes and enables reliable assessment of 3D spatial parallax for constructing high‑quality synthetic datasets.
arXiv:2608.23410v1 Announce Type: new Abstract: Photorealistic novel view synthesis of people remains challenging at high spatial resolutions and across multiple target cameras, where preserving iden...
arXiv:2607. 17790v1 Announce Type: cross Abstract: Egocentric devices, such as wearable front-facing cameras, provide a unique perspective for capturing the continuous interaction between a human viewer and the surrounding environment.
arXiv:2606. 19676v1 Announce Type: cross Abstract: Diffusion models have achieved remarkable success in image and video generation and editing.
Egocentric devices, such as wearable front-facing cameras, provide a unique perspective for capturing the continuous interaction between a human viewer and the surrounding environment. A holistic and efficient multimodal model capable of reconstructing this 4D representation is therefore highly desirable.
arXiv:2606. 31585v1 Announce Type: cross Abstract: The remarkable scalability of Transformers has expanded their application to 3D computer vision, where camera-aware positional encoding is crucial for providing spatial cues in multi-view geometry.
BooM-VVT is a mask‑free video virtual try‑on framework that builds on a keyframe‑driven paradigm. It uses a multi‑stage training strategy with image‑level pseudo data to learn mask‑free localization, introduces Garment‑Sensitive Keyframe Sampling to capture garment appearance, and employs Frame‑Shared 3D‑RoPE for spatiotemporal correspondence. The authors also create the OmniView dataset to support diverse camera viewpoints and tasks, achieving superior temporal consistency and garment fidelity compared to existing methods.
MINT is a foundation model that directly predicts world-space two-hand trajectories from egocentric RGB video, jointly estimating camera motion, hand states, and hand presence in a single spatiotemporal representation. It uses an open-source labeling pipeline, EGOPIPELINE, to generate large-scale pseudo-labels for pretraining, followed by fine-tuning on a small set of high-quality joint annotations. The model outperforms existing multi-stage approaches in accuracy and speed, and generalizes zero‑shot to unseen egocentric datasets.
arXiv:2607. 17097v2 Announce Type: replace Abstract: Hand-Object Interaction (HOI) synthesis is a cornerstone for animation production and embodied AI.
BooM‑VVT is a mask‑free video virtual try‑on framework that builds on a keyframe‑driven paradigm. It introduces a multi‑stage training strategy using image‑level pseudo data to learn mask‑free localization, a garment‑sensitive keyframe sampling method to capture garment appearance, and a Frame‑Shared 3D‑RoPE module to align keyframes with target video frames for accurate garment detail transfer. The authors also release OmniView, a large‑scale multi‑view try‑on dataset, and demonstrate that BooM‑VVT outperforms existing methods in temporal consistency and garment fidelity.
arXiv:2512. 16919v2 Announce Type: replace-cross Abstract: Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving.
arXiv:2605. 04035v3 Announce Type: replace-cross Abstract: We propose HeadsUp, a scalable feed-forward method for reconstructing high-quality 3D Gaussian heads from large-scale multi-camera setups.
Camera intrinsics are vital for recovering 3D structure from 2D video. However, most 3D algorithms assume fixed intrinsics throughout a video, an assumption that often fails for real-world in-the-wild videos.