Jack (in SF) Langerman
@jacklangerman.bsky.social
i mean the 1-3 minute version
September 22, 2025 at 4:20 PM
i mean the 1-3 minute version
Please reshare, tell you friends, give it a try, and don't hesitate to reach out to the team with any questions!
bsky.app/profile/jack...
bsky.app/profile/jack...
🚨 Just one month left to submit your solutions for The Structured Semantic 3D Reconstruction (S23DR-2025) Challenge!!! It is not too late to join!
Comp on @hf.co, part of the Workshop on Urban Scene Modeling at @cvprconference.bsky.social 2025
🔥$25,000 prize pool. Deadline: June 5, 2025.
🧵 (1/7)
Comp on @hf.co, part of the Workshop on Urban Scene Modeling at @cvprconference.bsky.social 2025
🔥$25,000 prize pool. Deadline: June 5, 2025.
🧵 (1/7)
May 6, 2025 at 11:29 PM
Please reshare, tell you friends, give it a try, and don't hesitate to reach out to the team with any questions!
bsky.app/profile/jack...
bsky.app/profile/jack...
🌍 Workshop + other challenges at:
usm3d.github.io
Let’s make SfM more structured.
Good luck, teams!
(7/7)
usm3d.github.io
Let’s make SfM more structured.
Good luck, teams!
(7/7)
2nd Workshop on Urban Scene Modeling: Where Vision Meets Photogrammetry and Graphics
CVPR 2025 Workshop on Urban Scene Modeling: Where Vision Meets Photogrammetry and Graphics.
usm3d.github.io
May 6, 2025 at 11:28 PM
🌍 Workshop + other challenges at:
usm3d.github.io
Let’s make SfM more structured.
Good luck, teams!
(7/7)
usm3d.github.io
Let’s make SfM more structured.
Good luck, teams!
(7/7)
📌 Want a clear reference?
Check out the example baseline submission:
huggingface.co/usm3d/handcr...
(6/7)
Check out the example baseline submission:
huggingface.co/usm3d/handcr...
(6/7)
usm3d/handcrafted_submission_2025 · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
May 6, 2025 at 11:28 PM
📌 Want a clear reference?
Check out the example baseline submission:
huggingface.co/usm3d/handcr...
(6/7)
Check out the example baseline submission:
huggingface.co/usm3d/handcr...
(6/7)
📊 NEW Evaluation Metric
Say goodbye to WED.
Hello to a human-aligned combo of:
• Vertex F1
• Edge IoU
Backed by this paper:
👉 arxiv.org/abs/2503.08208
Say goodbye to WED.
Hello to a human-aligned combo of:
• Vertex F1
• Edge IoU
Backed by this paper:
👉 arxiv.org/abs/2503.08208
Explaining Human Preferences via Metrics for Structured 3D Reconstruction
"What cannot be measured cannot be improved" while likely never uttered by Lord Kelvin, summarizes effectively the purpose of this work. This paper presents a detailed evaluation of automated metrics ...
arxiv.org
May 6, 2025 at 11:28 PM
📊 NEW Evaluation Metric
Say goodbye to WED.
Hello to a human-aligned combo of:
• Vertex F1
• Edge IoU
Backed by this paper:
👉 arxiv.org/abs/2503.08208
Say goodbye to WED.
Hello to a human-aligned combo of:
• Vertex F1
• Edge IoU
Backed by this paper:
👉 arxiv.org/abs/2503.08208
⚙️ All helper functions + data loaders:
pip install hoho2025
🛠️ Codebase: github.com/s23dr/hoho2025
(4/7)
pip install hoho2025
🛠️ Codebase: github.com/s23dr/hoho2025
(4/7)
GitHub - s23dr/hoho2025: Tools and utilities for the S23DR-2025 competition and HoHo25k Dataset
Tools and utilities for the S23DR-2025 competition and HoHo25k Dataset - s23dr/hoho2025
github.com
May 6, 2025 at 11:28 PM
⚙️ All helper functions + data loaders:
pip install hoho2025
🛠️ Codebase: github.com/s23dr/hoho2025
(4/7)
pip install hoho2025
🛠️ Codebase: github.com/s23dr/hoho2025
(4/7)
📦 New dataset:
hoho25k — 5x bigger than 2024!
• 25,000 scenes
• 8 images per scene
• 200,000 total images
📥 Get it here: huggingface.co/datasets/usm...
(3/7)
hoho25k — 5x bigger than 2024!
• 25,000 scenes
• 8 images per scene
• 200,000 total images
📥 Get it here: huggingface.co/datasets/usm...
(3/7)
usm3d/hoho25k · Datasets at Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
May 6, 2025 at 11:28 PM
📦 New dataset:
hoho25k — 5x bigger than 2024!
• 25,000 scenes
• 8 images per scene
• 200,000 total images
📥 Get it here: huggingface.co/datasets/usm...
(3/7)
hoho25k — 5x bigger than 2024!
• 25,000 scenes
• 8 images per scene
• 200,000 total images
📥 Get it here: huggingface.co/datasets/usm...
(3/7)
🧠 The task:
Turn multiview inputs (semantic segs, monocular depth) + SfM outputs (point clouds + camera poses) into sparse, geometrically accurate wireframes.
AKA: “More Structured Structure-from-Motion” 😎
Challenge page 👉 huggingface.co/spaces/usm3d...
(2/7)
Turn multiview inputs (semantic segs, monocular depth) + SfM outputs (point clouds + camera poses) into sparse, geometrically accurate wireframes.
AKA: “More Structured Structure-from-Motion” 😎
Challenge page 👉 huggingface.co/spaces/usm3d...
(2/7)
S23DR2025 - a Hugging Face Space by usm3d
This application allows you to view competition details, manage your submissions, and check leaderboards. You can access rules, dataset information, and view your own submissions and scores.
huggingface.co
May 6, 2025 at 11:28 PM
🧠 The task:
Turn multiview inputs (semantic segs, monocular depth) + SfM outputs (point clouds + camera poses) into sparse, geometrically accurate wireframes.
AKA: “More Structured Structure-from-Motion” 😎
Challenge page 👉 huggingface.co/spaces/usm3d...
(2/7)
Turn multiview inputs (semantic segs, monocular depth) + SfM outputs (point clouds + camera poses) into sparse, geometrically accurate wireframes.
AKA: “More Structured Structure-from-Motion” 😎
Challenge page 👉 huggingface.co/spaces/usm3d...
(2/7)
When I was working at Bell Labs in Murray Hill we used to specifically go to 3rd floor for coffee because the couch in that particular coffee room was (supposedly) Dennis Ritchie's.
was also a room with a whiteboard that may have been where Shannon did a lot of the info theory work.
good times
was also a room with a whiteboard that may have been where Shannon did a lot of the info theory work.
good times
March 27, 2025 at 3:37 PM
When I was working at Bell Labs in Murray Hill we used to specifically go to 3rd floor for coffee because the couch in that particular coffee room was (supposedly) Dennis Ritchie's.
was also a room with a whiteboard that may have been where Shannon did a lot of the info theory work.
good times
was also a room with a whiteboard that may have been where Shannon did a lot of the info theory work.
good times
do you think this is a matter of semantic disipline or genuine beliefs about qualia?
ie "with certain inputs models can produce outputs that contain patterns typically associated with anxiety in humans. asking them to perform mindfulness exercises can mitigate this behavior" vs "they feel anxious"?
ie "with certain inputs models can produce outputs that contain patterns typically associated with anxiety in humans. asking them to perform mindfulness exercises can mitigate this behavior" vs "they feel anxious"?
March 18, 2025 at 8:40 PM
do you think this is a matter of semantic disipline or genuine beliefs about qualia?
ie "with certain inputs models can produce outputs that contain patterns typically associated with anxiety in humans. asking them to perform mindfulness exercises can mitigate this behavior" vs "they feel anxious"?
ie "with certain inputs models can produce outputs that contain patterns typically associated with anxiety in humans. asking them to perform mindfulness exercises can mitigate this behavior" vs "they feel anxious"?
more blending between rings i think (~long range dependence)
March 15, 2025 at 10:50 PM
more blending between rings i think (~long range dependence)