Related papers: Any4D: Unified Feed-Forward Metric 4D Reconstructi…
Recent advancements in diffusion models for 2D and 3D content creation have sparked a surge of interest in generating 4D content. However, the scarcity of 3D scene datasets constrains current methodologies to primarily object-centric…
Models for egocentric 3D and 4D reconstruction, including few-shot interpolation and extrapolation settings, can benefit from having images from exocentric viewpoints as supervision signals. No existing dataset provides the necessary…
In this paper, we present Consistent4D, a novel approach for generating 4D dynamic objects from uncalibrated monocular videos. Uniquely, we cast the 360-degree dynamic object reconstruction as a 4D generation problem, eliminating the need…
A long-standing goal in scene understanding is to obtain interpretable and editable representations that can be directly constructed from a raw monocular RGB-D video, without requiring specialized hardware setup or priors. The problem is…
In the last year, universal monocular metric depth estimation (universal MMDE) has gained considerable attention, serving as the foundation model for various multimedia tasks, such as video and image editing. Nonetheless, current approaches…
Generative video models have significantly advanced the photorealistic synthesis of adverse weather for autonomous driving; however, they consistently demand massive datasets to learn rare weather scenarios. While 3D-aware editing methods…
We present a novel framework for dynamic radiance field prediction given monocular video streams. Unlike previous methods that primarily focus on predicting future frames, our method goes a step further by generating explicit 3D…
Current compositional image-to-3D scene generation approaches construct 3D scenes by time-consuming iterative layout optimization or inflexible joint object-layout generation. Moreover, most methods rely on limited field-of-view perspective…
Feedforward Gaussian Splatting has recently emerged as an efficient paradigm for 4D reconstruction in autonomous driving. However, in unstructured off-road scenes, its performance degrades due to high-frequency geometry, ego-motion jitter,…
Dynamic driving scene reconstruction is critical for autonomous driving simulation and closed-loop learning. While recent feed-forward methods have shown promise for 3D reconstruction, they struggle with long-range driving sequences due to…
Existing techniques for dynamic scene reconstruction from multiple wide-baseline cameras primarily focus on reconstruction in controlled environments, with fixed calibrated cameras and strong prior constraints. This paper introduces a…
We address the problem of dynamic scene reconstruction from sparse-view videos. Prior work often requires dense multi-view captures with hundreds of calibrated cameras (e.g. Panoptic Studio). Such multi-view setups are prohibitively…
Recent advances in diffusion-based generative models have established a new paradigm for image and video relighting. However, extending these capabilities to 4D relighting remains challenging, due primarily to the scarcity of paired 4D…
Monocular depth estimation aims to recover the depth information of 3D scenes from 2D images. Recent work has made significant progress, but its reliance on large-scale datasets and complex decoders has limited its efficiency and…
In the realm of robot-assisted minimally invasive surgery, dynamic scene reconstruction can significantly enhance downstream tasks and improve surgical outcomes. Neural Radiance Fields (NeRF)-based methods have recently risen to prominence…
This paper targets high-fidelity and real-time view synthesis of dynamic 3D scenes at 4K resolution. Recently, some methods on dynamic view synthesis have shown impressive rendering quality. However, their speed is still limited when…
High-fidelity rendering of dynamic humans from monocular videos typically degrades catastrophically under occlusions. Existing solutions incorporate external priors-either hallucinating missing content via generative models, which induces…
Foundation models pre-trained on massive unlabeled datasets have revolutionized natural language and computer vision, exhibiting remarkable generalization capabilities, thus highlighting the importance of pre-training. Yet, efforts in…
Active 3D reconstruction enables an agent to autonomously select viewpoints to efficiently obtain accurate and complete scene geometry, rather than passively reconstructing scenes from pre-collected images. However, existing active…
In this study, we address the challenge of 3D scene structure recovery from monocular depth estimation. While traditional depth estimation methods leverage labeled datasets to directly predict absolute depth, recent advancements advocate…