Repository navigation
FEATURE: Add resize/crop visual encoders - #178
Merged
Merged
Conversation
Camera capture resolution and encoder output resolution were previously conflated (the same HxW drove both). Adds and encoder_ids so a camera can capture at one resolution (hardware-native, or shared across tasks) while the observation is resized/center-cropped to whatever a downstream model needs, using torchvision to stay consistent with the existing r3m/rrl/vc1 transform pipelines. Documents the visual_keys format and design rationale in robohive/envs/VISUAL_ENCODERS.md.
andreh1111
approved these changes
Aug 13, 2026
akssri
approved these changes
Aug 14, 2026
akssri
left a comment
akssri
left a comment
There was a problem hiding this comment.
LGTM
(tested this on a env; patched examine_env.py in anthrohive)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Camera capture resolution and encoder output resolution were previously conflated (the same HxW drove both). Adds and
encoder_ids so a camera can capture at one resolution
(hardware-native, or shared across tasks) while the observation is resized/center-cropped to whatever a downstream model needs, using torchvision to stay consistent with the existing r3m/rrl/vc1 transform pipelines. Documents the visual_keys format and design rationale in robohive/envs/VISUAL_ENCODERS.md.