diff --git a/README.md b/README.md
index db75273d99b9606bcb8d3cf9695565b85e48985c..bdf06b55e32fda8788d8c62bb361e5f7504cda7f 100644
--- a/README.md
+++ b/README.md
@@ -262,7 +262,7 @@ __Q:__ The NeRF reconstruction of my custom dataset looks bad; what can I do?
 __A:__ There could be multiple issues:
 - COLMAP might have been unable to reconstruct camera poses.
 - There might have been movement or blur during capture. Don't treat capture as an artistic task; treat it as photogrammetry. You want _\*as little blur as possible\*_ in your dataset (motion, defocus, or otherwise) and all objects must be _\*static\*_ during the entire capture. Bonus points if you are using a wide-angle lens (iPhone wide angle works well), because it covers more space than narrow lenses.
-- The dataset parameters (in particular `aabb_scale`) might have been tuned suboptimally. We recommend starting with `aabb_scale=16` and then increasing or decreasing it by factors of two until you get optimal quality.
+- The dataset parameters (in particular `aabb_scale`) might have been tuned suboptimally. We recommend starting with `aabb_scale=128` and then increasing or decreasing it by factors of two until you get optimal quality.
 - Carefully read [our NeRF training & dataset tips](https://github.com/NVlabs/instant-ngp/blob/master/docs/nerf_dataset_tips.md).
 
 ##
diff --git a/docs/nerf_dataset_tips.md b/docs/nerf_dataset_tips.md
index d5f982429dae4e9edf26c02720ce1042a14e9900..de311e80e227caca34fc73203ef42bcf433001d0 100644
--- a/docs/nerf_dataset_tips.md
+++ b/docs/nerf_dataset_tips.md
@@ -43,7 +43,7 @@ If you have an existing dataset in `transforms.json` format, it should be center
 You can set any of the following parameters, where the listed values are the default.
 ```json
 {
-	"aabb_scale": 16,
+	"aabb_scale": 64,
 	"scale": 0.33,
 	"offset": [0.5, 0.5, 0.5],
 	...	
@@ -88,7 +88,7 @@ If you use Windows, you do not need to install anything. COLMAP and FFmpeg will
 If you are training from a video file, run the [scripts/colmap2nerf.py](/scripts/colmap2nerf.py) script from the folder containing the video, with the following recommended parameters:
 
 ```sh
-data-folder$ python [path-to-instant-ngp]/scripts/colmap2nerf.py --video_in <filename of video> --video_fps 2 --run_colmap --aabb_scale 16
+data-folder$ python [path-to-instant-ngp]/scripts/colmap2nerf.py --video_in <filename of video> --video_fps 2 --run_colmap --aabb_scale 64
 ```
 
 The above assumes a single video file as input, which then has frames extracted at the specified framerate (2). It is recommended to choose a frame rate that leads to around 50-150 images. So for a one minute video, `--video_fps 2` is ideal.
@@ -96,7 +96,7 @@ The above assumes a single video file as input, which then has frames extracted
 For training from images, place them in a subfolder called `images` and then use suitable options such as the ones below:
 
 ```sh
-data-folder$ python [path-to-instant-ngp]/scripts/colmap2nerf.py --colmap_matcher exhaustive --run_colmap --aabb_scale 16
+data-folder$ python [path-to-instant-ngp]/scripts/colmap2nerf.py --colmap_matcher exhaustive --run_colmap --aabb_scale 64
 ```
 
 The script will run (and install, if you use Windows) FFmpeg and COLMAP as needed, followed by a conversion step to the required `transforms.json` format, which will be written in the current directory. 
@@ -104,7 +104,7 @@ The script will run (and install, if you use Windows) FFmpeg and COLMAP as neede
 By default, the script invokes colmap with the "sequential matcher", which is suitable for images taken from a smoothly changing camera path, as in a video. The exhaustive matcher is more appropriate if the images are in no particular order, as shown in the image example above.
 For more options, you can run the script with `--help`. For more advanced uses of COLMAP or for challenging scenes, please see the [COLMAP documentation](https://colmap.github.io/cli.html); you may need to modify the [scripts/colmap2nerf.py](/scripts/colmap2nerf.py) script itself.
 
-The `aabb_scale` parameter is the most important `instant-ngp` specific parameter. It specifies the extent of the scene, defaulting to 1; that is, the scene is scaled such that the camera positions are at an average distance of 1 unit from the origin. For small synthetic scenes such as the original NeRF dataset, the default `aabb_scale` of 1 is ideal and leads to fastest training. The NeRF model makes the assumption that the training images can entirely be explained by a scene contained within this bounding box. However, for natural scenes where there is a background that extends beyond this bounding box, the NeRF model will struggle and may hallucinate "floaters" at the boundaries of the box. By setting `aabb_scale` to a larger power of 2 (up to a maximum of 16), the NeRF model will extend rays to a much larger bounding box. Note that this can impact training speed slightly. If in doubt, for natural scenes, start with an `aabb_scale` of 128, and subsequently reduce it if possible. The value can be directly edited in the `transforms.json` output file, without re-running the [scripts/colmap2nerf.py](/scripts/colmap2nerf.py) script.
+The `aabb_scale` parameter is the most important `instant-ngp` specific parameter. It specifies the extent of the scene, defaulting to 1; that is, the scene is scaled such that the camera positions are at an average distance of 1 unit from the origin. For small synthetic scenes such as the original NeRF dataset, the default `aabb_scale` of 1 is ideal and leads to fastest training. The NeRF model makes the assumption that the training images can entirely be explained by a scene contained within this bounding box. However, for natural scenes where there is a background that extends beyond this bounding box, the NeRF model will struggle and may hallucinate "floaters" at the boundaries of the box. By setting `aabb_scale` to a larger power of 2 (up to a maximum of 128), the NeRF model will extend rays to a much larger bounding box. Note that this can impact training speed slightly. If in doubt, for natural scenes, start with an `aabb_scale` of 128, and subsequently reduce it if possible. The value can be directly edited in the `transforms.json` output file, without re-running the [scripts/colmap2nerf.py](/scripts/colmap2nerf.py) script.
 
 You can optionally pass in object categories (e.g. `--mask_categories person car`) which runs [Detectron2](https://github.com/facebookresearch/detectron2) to generate masks automatically.
 __instant-ngp__ will not use the masked pixels for training.
diff --git a/scripts/colmap2nerf.py b/scripts/colmap2nerf.py
index 88ba5e67d6e261aae7d0dd26feafa63566e4c74b..68d6bd9ece6a74588e8ac87f9197d8c9da910079 100755
--- a/scripts/colmap2nerf.py
+++ b/scripts/colmap2nerf.py
@@ -37,7 +37,7 @@ def parse_args():
 	parser.add_argument("--colmap_camera_params", default="", help="Intrinsic parameters, depending on the chosen model. Format: fx,fy,cx,cy,dist")
 	parser.add_argument("--images", default="images", help="Input path to the images.")
 	parser.add_argument("--text", default="colmap_text", help="Input path to the colmap text files (set automatically if --run_colmap is used).")
-	parser.add_argument("--aabb_scale", default=16, choices=["1", "2", "4", "8", "16", "32", "64", "128"], help="Large scene scale factor. 1=scene fits in unit cube; power of 2 up to 128")
+	parser.add_argument("--aabb_scale", default=64, choices=["1", "2", "4", "8", "16", "32", "64", "128"], help="Large scene scale factor. 1=scene fits in unit cube; power of 2 up to 128")
 	parser.add_argument("--skip_early", default=0, help="Skip this many images from the start.")
 	parser.add_argument("--keep_colmap_coords", action="store_true", help="Keep transforms.json in COLMAP's original frame of reference (this will avoid reorienting and repositioning the scene for preview and rendering).")
 	parser.add_argument("--out", default="transforms.json", help="Output path.")