Recent advances in neural reconstruction enable high-quality 3D object reconstruction from casually captured image collections. Current techniques mostly analyze their progress on relatively simple image collections where Structure-from-Motion (SfM) techniques can provide ground-truth (GT) camera poses.

The ability to sense and reconstruct 3D appearance and geometry is critical to applications in vision, graphics, and beyond.

In this paper, we propose the M asked S pace-T ime H ash encoding (MSTH), a novel method for efficiently reconstructing dynamic 3D scenes from multi-view or monoc-ular videos.

These estimates are subsequently utilized to aggregate information from reference frames into the target frame. Subsequently, hierarchical neural point clouds are constructed based on the aggregated information. This hierarchical point cloud set is then employed to synthesize views of the target frame.

We introduce Stanford-ORB, a new real-world 3D Object inverse Rendering Benchmark.

Neural Radiance Fields (NeRFs) have achieved impressive results in novel view synthesis and surface reconstruction tasks.

We present a method for text-driven perpetual view generation - synthesizing long-term videos of various scenes solely from an input text prompt describing the scene and camera poses.

Synthesizing novel photo-realistic views of captured 3D scenes is important for many domains including virtual/augmented reality, video games or movie productions.