- Academic Search

Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?

JH Lee, G Mikriukov, G Schwalbe, S Wermter… - ar**, and retrieving, is a critical challenge for
robot manipulation tasks. Existing methods primarily focus on table-top scenarios, which do …

Save Cite Cited by 1 Related articles View as HTML

MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data

H Jiang, Z Xu, D **e, Z Chen, H **, F Luan… - arxiv preprint arxiv …, 2024 - arxiv.org

We propose scaling up 3D scene reconstruction by training with synthesized data. At the
core of our work is MegaSynth, a procedurally generated 3D dataset comprising 700K …

Scene Co-pilot: Procedural Text to Video Generation with Human in the Loop

Z Qian, A Sharifi, T Carroll, SN Lim - arxiv preprint arxiv:2411.18644, 2024 - arxiv.org

Video generation has achieved impressive quality, but it still suffers from artifacts such as
temporal inconsistency and violation of physical laws. Leveraging 3D scenes can …

AutoVFX: Physically Realistic Video Editing from Natural Language Instructions

HY Hsu, ZH Lin, A Zhai, H **a, S Wang - arxiv preprint arxiv:2411.02394, 2024 - arxiv.org

Modern visual effects (VFX) software has made it possible for skilled artists to create imagery
of virtually anything. However, the creation process remains laborious, complex, and largely …

DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation

W Zhao, YP Cao, J Xu, Y Dong, Y Shan - arxiv preprint arxiv:2412.15200, 2024 - arxiv.org

Procedural Content Generation (PCG) is powerful in creating high-quality 3D contents, yet
controlling it to produce desired shapes is difficult and often requires extensive parameter …

Holistic Understanding of 3D Scenes as Universal Scene Description

AM Halacheva, Y Miao, JN Zaech, X Wang… - arxiv preprint arxiv …, 2024 - arxiv.org

3D scene understanding is a long-standing challenge in computer vision and a key
component in enabling mixed reality, wearable computing, and embodied AI. Providing a …

HouseCrafter: Lifting Floorplans to 3D Scenes with 2D Diffusion Model

HT Nguyen, Y Chen, V Voleti, V Jampani… - arxiv preprint arxiv …, 2024 - arxiv.org

We introduce HouseCrafter, a novel approach that can lift a floorplan into a complete large
3D indoor scene (eg, a house). Our key insight is to adapt a 2D diffusion model, which is …