Skip to content

GitLab

"vscode:/vscode.git/clone" did not exist on "ca1c7af21b75d57771351170a98102a024d219c0"
Unverified Commit 346dd51a authored by Ruilong Li(李瑞龙)'s avatar Ruilong Li(李瑞龙) Committed by GitHub
Browse files

update dnerf perf (#61)

parent 127223b1
Show whitespace changes
Inline Side-by-side
Showing with 3 additions and 3 deletions
README.md
View file @ 346dd51a
...@@ -14,7 +14,7 @@ Using NerfAcc, ...@@ -14,7 +14,7 @@ Using NerfAcc,
- The `Instant-NGP NeRF` model can be trained to *better quality* (+~0.7 PSNR) with *9/10th* of - The `Instant-NGP NeRF` model can be trained to *better quality* (+~0.7 PSNR) with *9/10th* of
the training time (4.5 minutes) comparing to the official pure-CUDA implementation. the training time (4.5 minutes) comparing to the official pure-CUDA implementation.
- The `D-NeRF` model for *dynamic* objects can also be trained in *1 hour* - The `D-NeRF` model for *dynamic* objects can also be trained in *1 hour*
rather than *2 days* as in the paper, and with *better quality* (+~2.0 PSNR). rather than *2 days* as in the paper, and with *better quality* (+~2.5 PSNR).
- Both *bounded* and *unbounded* scenes are supported. - Both *bounded* and *unbounded* scenes are supported.
**And it is pure Python interface with flexible APIs!** **And it is pure Python interface with flexible APIs!**
......
docs/source/examples/dnerf.rst
View file @ 346dd51a
...@@ -23,7 +23,7 @@ single NVIDIA TITAN RTX GPU. The training memory footprint is about 11GB. ...@@ -23,7 +23,7 @@ single NVIDIA TITAN RTX GPU. The training memory footprint is about 11GB.
| PSNR | bouncing | hell | hook | jumping | lego | mutant | standup | trex | MEAN | | PSNR | bouncing | hell | hook | jumping | lego | mutant | standup | trex | MEAN |
| | balls | warrior | | jacks | | | | | | | | balls | warrior | | jacks | | | | | |
+======================+==========+=========+=======+=========+=======+========+=========+=======+=======+ +======================+==========+=========+=======+=========+=======+========+=========+=======+=======+
| D-Nerf (~ days) | 38.93 | 25.02 | 29.25 | 32.80 | 21.64 | 31.29 | 32.79 | 31.75 | 30.43 | | D-Nerf (~ days) | 32.80 | 25.02 | 29.25 | 32.80 | 21.64 | 31.29 | 32.79 | 31.75 | 29.67 |
+----------------------+----------+---------+-------+---------+-------+--------+---------+-------+-------+ +----------------------+----------+---------+-------+---------+-------+--------+---------+-------+-------+
| Ours (~ 1 hr) | 39.49 | 25.58 | 31.86 | 32.73 | 24.32 | 35.55 | 35.90 | 32.33 | 32.22 | | Ours (~ 1 hr) | 39.49 | 25.58 | 31.86 | 32.73 | 24.32 | 35.55 | 35.90 | 32.33 | 32.22 |
+----------------------+----------+---------+-------+---------+-------+--------+---------+-------+-------+ +----------------------+----------+---------+-------+---------+-------+--------+---------+-------+-------+
......
docs/source/index.rst
View file @ 346dd51a
...@@ -11,7 +11,7 @@ Using NerfAcc, ...@@ -11,7 +11,7 @@ Using NerfAcc,
- The `Instant-NGP Nerf`_ model can be trained to *better quality* (+~0.7 PSNR) with *9/10th* of \ - The `Instant-NGP Nerf`_ model can be trained to *better quality* (+~0.7 PSNR) with *9/10th* of \
the training time (4.5 minutes) comparing to the official pure-CUDA implementation. the training time (4.5 minutes) comparing to the official pure-CUDA implementation.
- The `D-Nerf`_ model for *dynamic* objects can also be trained in *1 hour* \ - The `D-Nerf`_ model for *dynamic* objects can also be trained in *1 hour* \
rather than *2 days* as in the paper, and with *better quality* (+~2.0 PSNR). rather than *2 days* as in the paper, and with *better quality* (+~2.5 PSNR).
- Both *bounded* and *unbounded* scenes are supported. - Both *bounded* and *unbounded* scenes are supported.
**And it is pure Python interface with flexible APIs!** **And it is pure Python interface with flexible APIs!**
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment