DAVIS-dance-twirl (90 frames). From left to right: reference video, results of LASR, results of VIBE+SMPLify, and results of ViSER. Top: reconstructed 3D shape. Bottom: reconstructed 3D shape at 1st frame.

---

DAVIS-breakdance-flare. From left to right: reference video, results of LASR, results of VIBE+SMPLify, and results of ViSER. Top: reconstructed 3D shape. Bottom: reconstructed 3D shape at 1st frame.

---

DAVIS-breakdance. From left to right: reference video, results of LASR, results of VIBE+SMPLify, and results of ViSER. Top: reconstructed 3D shape. Bottom: reconstructed 3D shape at 1st frame. VIBE+SMPLify fails to reconstruct most of the frames in this video.

---

DAVIS-parkour. From left to right: reference video, results of LASR, results of VIBE+SMPLify, and results of ViSER. Top: reconstructed 3D shape. Bottom: reconstructed 3D shape at 1st frame.

---

DAVIS-ballet-1. From left to right: reference video, results of LASR, results of VIBE+SMPLify, and results of ViSER. Top: reconstructed 3D shape. Bottom: reconstructed 3D shape at 1st frame.

---

DAVIS-ballet-2. From left to right: reference video, results of LASR, results of VIBE+SMPLify, and results of ViSER. Top: reconstructed 3D shape. Bottom: reconstructed 3D shape at 1st frame.

---

DAVIS-ballet-3. From left to right: reference video, results of LASR, results of VIBE+SMPLify, and results of ViSER. Top: reconstructed 3D shape. Bottom: reconstructed 3D shape at 1st frame.

---

YTVOS-Elephants. From top to bottom: reference video, results of LASR, and results of ViSER. Reconstruction on the 1st frame is shown.