Related papers: PhyMix: Towards Physically Consistent Single-Image…
Scene synthesis and editing has emerged as a promising direction in computer graphics. Current trained approaches for 3D indoor scene generation either oversimplify object semantics through one-hot class encodings (e.g., 'chair' or…
We present a method to edit complex indoor lighting from a single image with its predicted depth and light source segmentation masks. This is an extremely challenging problem that requires modeling complex light transport, and disentangling…
Recent conditional image synthesis approaches provide high-quality synthesized images. However, it is still challenging to accurately adjust image contents such as the positions and orientations of objects, and synthesized images often have…
Crafting a single, versatile physics-based controller that can breathe life into interactive characters across a wide spectrum of scenarios represents an exciting frontier in character animation. An ideal controller should support diverse…
Generating good quality and geometrically plausible synthetic images of humans with the ability to control appearance, pose and shape parameters, has become increasingly important for a variety of tasks ranging from photo editing, fashion…
As Artificial Intelligence Generated Content (AIGC) advances, a variety of methods have been developed to generate text, images, videos, and 3D objects from single or multimodal inputs, contributing efforts to emulate human-like cognitive…
Inferring the physical properties of 3D scenes from visual information is a critical yet challenging task for creating interactive and realistic virtual worlds. While humans intuitively grasp material characteristics such as elasticity or…
Learning-based methods for 3D scene reconstruction and object completion require large datasets containing partial scans paired with complete ground-truth geometry. However, acquiring such datasets using real-world scanning systems is…
Simulation is a central tool for scalable robot learning, but its effectiveness depends on the quality of object assets. While modern 3D datasets provide rich geometric and kinematic representations, they typically lack the physical…
To achieve realistic immersion in landscape images, fluids such as water and clouds need to move within the image while revealing new scenes from various camera perspectives. Recently, a field called dynamic scene video has emerged, which…
3D generative AI enables rapid and accessible creation of 3D models from text or image inputs. However, translating these outputs into physical objects remains a challenge due to the constraints in the physical world. Recent studies have…
Despite significant advances in video generation, synthesizing physically plausible human actions remains a persistent challenge, particularly in modeling fine-grained semantics and complex temporal dynamics. For instance, generating…
Recently, the surge of efficient and automated 3D AI-generated content (AIGC) methods has increasingly illuminated the path of transforming human imagination into complex 3D structures. However, the automated generation of 3D content is…
High-quality 3D scene generation from a single image is crucial for AR/VR and embodied AI applications. Early approaches struggle to generalize due to reliance on specialized models trained on curated small datasets. While recent…
Foundation models have achieved remarkable success across video, image, and language domains. By scaling up the number of parameters and training datasets, these models acquire generalizable world knowledge and often surpass task-specific…
Holistic 3D indoor scene understanding refers to jointly recovering the i) object bounding boxes, ii) room layout, and iii) camera pose, all in 3D. The existing methods either are ineffective or only tackle the problem partially. In this…
Existing generative approaches for guided image synthesis of multi-object scenes typically rely on 2D controls in the image or text space. As a result, these methods struggle to maintain and respect consistent three-dimensional geometric…
The creation of high-fidelity, customizable 3D indoor scene textures remains a significant challenge. While text-driven methods offer flexibility, they lack the precision for fine-grained, instance-level control, and often produce textures…
3D scene generation has quickly become a challenging new research direction, fueled by consistent improvements of 2D generative diffusion models. Most prior work in this area generates scenes by iteratively stitching newly generated frames…
Synthetic 3D scenes are essential for developing Physical AI and generative models. Existing procedural generation methods often have low output throughput, creating a significant bottleneck in scaling up dataset creation. In this work, we…