Related papers: ReplicateAnyScene: Zero-Shot Video-to-3D Compositi…
Many compelling video processing effects can be achieved if per-pixel depth information and 3D camera calibrations are known. However, the success of such methods is highly dependent on the accuracy of this "scene-space" information. We…
Traditionally, 3D scene synthesis requires expert knowledge and significant manual effort. Automating this process could greatly benefit fields such as architectural design, robotics simulation, virtual reality, and gaming. Recent…
Recent CLIP-guided 3D optimization methods, such as DreamFields and PureCLIPNeRF, have achieved impressive results in zero-shot text-to-3D synthesis. However, due to scratch training and random initialization without prior knowledge, these…
Developing deep neural networks to generate 3D scenes is a fundamental problem in neural synthesis with immediate applications in architectural CAD, computer graphics, as well as in generating virtual robot training environments. This task…
Human dance generation (HDG) aims to synthesize realistic videos from images and sequences of driving poses. Despite great success, existing methods are limited to generating videos of a single person with specific backgrounds, while the…
Acquiring detailed 3D scenes typically demands costly equipment, multi-view data, or labor-intensive modeling. Therefore, a lightweight alternative, generating complex 3D scenes from a single top-down image, plays an essential role in…
The whole is greater than the sum of its parts-even in 3D-text contrastive learning. We introduce SceneForge, a novel framework that enhances contrastive alignment between 3D point clouds and text through structured multi-object scene…
Reconstructing physically stable 3D scenes from a single RGB image enables casual images to be converted into simulation-ready digital assets for applications such as immersive interaction and content creation. However, existing…
Automatically generating a complete 3D scene from a text description, a reference image, or both has significant applications in fields like virtual reality and gaming. However, current methods often generate low-quality textures and…
We explore the task of embodied view synthesis from monocular videos of deformable scenes. Given a minute-long RGBD video of people interacting with their pets, we render the scene from novel camera trajectories derived from the in-scene…
Reconstructing detailed 3D scenes from single-view images remains a challenging task due to limitations in existing approaches, which primarily focus on geometric shape recovery, overlooking object appearances and fine shape details. To…
The impressive performance of deep convolutional neural networks in single-view 3D reconstruction suggests that these models perform non-trivial reasoning about the 3D structure of the output space. Recent work has challenged this belief,…
Current 3D scene understanding methods are limited by offline-collected multi-view data or pre-constructed 3D geometry. In this paper, we present ExtractAnything3D (EA3D), a unified online framework for open-world 3D object extraction that…
Recent advances in 3D foundation models have led to growing interest in reconstructing humans and their surrounding environments. However, most existing approaches focus on monocular inputs, and extending them to multi-view settings…
Visual scenes are composed of visual concepts and have the property of combinatorial explosion. An important reason for humans to efficiently learn from diverse visual scenes is the ability of compositional perception, and it is desirable…
In this paper, we propose an adaptive keyframe selection method for improved 3D scene reconstruction in dynamic environments. The proposed method integrates two complementary modules: an error-based selection module utilizing photometric…
Traditional image-to-3D models often struggle with scenes containing multiple objects due to biases and occlusion complexities. To address this challenge, we present REPARO, a novel approach for compositional 3D asset generation from single…
Recent works on dynamic 3D neural field reconstruction assume the input from synchronized multi-view videos whose poses are known. The input constraints are often not satisfied in real-world setups, making the approach impractical. We show…
Embodied AI (EAI) research requires high-quality, diverse 3D scenes to effectively support skill acquisition, sim-to-real transfer, and generalization. Achieving these quality standards, however, necessitates the precise replication of…
With the proliferation of small aerial vehicles, acquiring close up aerial imagery for high quality reconstruction of complex scenes is gaining importance. We present an adaptive view planning method to collect such images in an automated…