ViSER: Video Surface Embeddings for Articulated 3D Shape Reconstruction

Results on YTVOS-elephants

Elephant-1. Top left: reference video. Top middle: reconstructed nonrigid 3D shape. Top right: reconstruction 3D shape at 1st frame. Bottom left: trajectory. Bottom middle: part segmnetation. Bottom right: textured mesh.

Elephant-2. Top left: reference video. Top middle: reconstructed nonrigid 3D shape. Top right: reconstruction 3D shape at 1st frame. Bottom left: trajectory. Bottom middle: part segmnetation. Bottom right: textured mesh.

Elephant-3. Top left: reference video. Top middle: reconstructed nonrigid 3D shape. Top right: reconstruction 3D shape at 1st frame. Bottom left: trajectory. Bottom middle: part segmnetation. Bottom right: textured mesh.

Elephant-4. Top left: reference video. Top middle: reconstructed nonrigid 3D shape. Top right: reconstruction 3D shape at 1st frame. Bottom left: trajectory. Bottom middle: part segmnetation. Bottom right: textured mesh.

Elephant-5. Top left: reference video. Top middle: reconstructed nonrigid 3D shape. Top right: reconstruction 3D shape at 1st frame. Bottom left: trajectory. Bottom middle: part segmnetation. Bottom right: textured mesh.

Elephant-6. Top left: reference video. Top middle: reconstructed nonrigid 3D shape. Top right: reconstruction 3D shape at 1st frame. Bottom left: trajectory. Bottom middle: part segmnetation. Bottom right: textured mesh.

Elephant-7. Top left: reference video. Top middle: reconstructed nonrigid 3D shape. Top right: reconstruction 3D shape at 1st frame. Bottom left: trajectory. Bottom middle: part segmnetation. Bottom right: textured mesh.