We introduce TransformerFusion, a transformer-based 3D scene reconstruction approach.
From an input monocular RGB video, the video frames are processed by a transformer …

We extend neural 3D representations to allow for intuitive and interpretable user control
beyond novel view rendering (ie camera control). We allow the user to annotate which part …

We introduce DoubleField, a novel framework combining the merits of both surface field and
radiance field for high-fidelity human reconstruction and rendering. Within DoubleField, the …

Obtaining personalized 3D animatable avatars from a monocular camera has several real
world applications in gaming, virtual try-on, animation, and VR/XR, etc. However, it is very …

This work targets at using a general deep learning framework to synthesize free-viewpoint
images of arbitrary human performers, only requiring a sparse number of camera views as …

In this work we develop a generalizable and efficient Neural Radiance Field (NeRF) pipeline
for high-fidelity free-viewpoint human body synthesis under settings with sparse camera …

Existing neural human rendering methods struggle with a single image input due to the lack
of information in in-visible areas and the depth ambiguity of pixels in visible areas. In this …

Dense correspondence between humans carries powerful semantic information that can be
utilized to solve fundamental problems for full-body understanding such as in-the-wild …

The increasing availability of video recordings made by multiple cameras has offered new
means for mitigating occlusion and depth ambiguities in pose and motion reconstruction …

We propose a novel framework to reconstruct super-resolution human shape from a single
low-resolution input image. The approach overcomes limitations of existing approaches that …