🏣 CityGaussianV2: Large-Scale City 🏣

👉A novel approach for large-scale scene reconstruction that addresses critical challenges related to geometric accuracy and efficiency: 10x compression, 25% faster & -50% memory! Source code released💙

👉Review https://t.ly/Xgn59
👉Paper arxiv.org/pdf/2411.00771
👉Project dekuliutesla.github.io/CityGaussianV2/
👉Code github.com/DekuLiuTesla/CityGaussian

💪 Muscles in Time Dataset 💪

👉Muscles in Time (MinT) is a large-scale synthetic muscle activation dataset. MinT contains 9+ hours of simulation data covering 227 subjects and 402 simulated muscle strands. Code & Dataset available soon 💙

👉Review https://t.ly/108g6
👉Paper arxiv.org/pdf/2411.00128
👉Project davidschneider.ai/mint
👉Code github.com/simplexsigil/MusclesInTime

🧠 Single Neuron Reconstruction 🧠

👉SIAT unveils NeuroFly, a framework for large-scale single neuron reconstruction. Formulating neuron reconstruction task as a 3-stage streamlined workflow: automatic segmentation - connection - manual proofreading. Bridging computer vision and neuroscience 💙

👉Review https://t.ly/Y5Xu0
👉Paper https://arxiv.org/pdf/2411.04715
👉Repo github.com/beanli161514/neurofly

🫠 X-Portrait 2: SOTA(?) Portrait Animation 🫠

👉ByteDance unveils a preview of X-Portrait2, the new SOTA expression encoder model that implicitly encodes every minuscule expressions from the input by training it on large-scale datasets. Impressive results but no paper & code announced.

👉Review https://t.ly/8Owh9 [UPDATE]
👉Paper ?
👉Project byteaigc.github.io/X-Portrait2/
👉Repo ?

❄️Don’t Look Twice: ViT by RLT❄️

👉CMU unveils RLT: speeding up the video transformers inspired by run-length encoding for data compression. Speed the training up and reducing the token count by up to 80%! Source Code announced 💙

👉Review https://t.ly/ccSwN
👉Paper https://lnkd.in/d6VXur_q
👉Project https://lnkd.in/d4tXwM5T
👉Repo TBA

🐔SeedEdit: foundational T2I🐔

👉ByteDance unveils a novel T2I foundational model capable of delivering stable, high-aesthetic image edits which maintain image quality through unlimited rounds of editing instructions. No code announced but a Demo is online💙

👉Review https://t.ly/hPlnN
👉Paper https://arxiv.org/pdf/2411.06686
👉Project team.doubao.com/en/special/seededit
🤗Demo https://huggingface.co/spaces/ByteDance/SeedEdit-APP

🔥 4 NanoSeconds inference 🔥

👉LogicTreeNet: convolutional differentiable logic gate net. with logic gate tree kernels: Computer Vision into differentiable LGNs. Up to 6100% smaller than SOTA, inference in 4 NANOsecs!

👉Review https://t.ly/GflOW
👉Paper https://lnkd.in/dAZQr3dW
👉Full clip https://lnkd.in/dvDJ3j-u

🛥️ Global Tracklet Association MOT 🛥️

👉A novel universal, model-agnostic method designed to refine and enhance tracklet association for single-camera MOT. Suitable for datasets such as SportsMOT, SoccerNet & similar. Source code released💙

👉Review https://t.ly/gk-yh
👉Paper https://lnkd.in/dvXQVKFw
👉Repo https://lnkd.in/dEJqiyWs

🧶 MagicQuill: super-easy Diffusion Editing 🧶

👉MagicQuill is a novel system designed to support users in smart editing of images. Robust UI/UX (e.g., inserting/erasing objects, colors, etc.) under a multimodal LLM to anticipate user intentions in real time. Code & Demos released 💙

👉Review https://t.ly/hJyLa
👉Paper https://arxiv.org/pdf/2411.09703
👉Project https://magicquill.art/demo/
👉Repo https://github.com/magic-quill/magicquill
👉Demo https://huggingface.co/spaces/AI4Editing/MagicQuill

🧰 EchoMimicV2: Semi-body Human 🧰

👉Alipay (ANT Group) unveils EchoMimicV2, the novel SOTA half-body human animation via APD-Harmonization. See clip with audio (ZH/ENG). Code & Demo announced💙

👉Review https://t.ly/enLxJ
👉Paper arxiv.org/pdf/2411.10061
👉Project antgroup.github.io/ai/echomimic_v2/
👉Repo-v2 github.com/antgroup/echomimic_v2
👉Repo-v1 https://github.com/antgroup/echomimic

⚔️SAMurai: SAM for Tracking⚔️

👉UWA unveils SAMURAI, an enhanced adaptation of SAM 2 specifically designed for visual object tracking. New SOTA! Code under Apache 2.0💙

👉Review https://t.ly/yGU0P
👉Paper https://arxiv.org/pdf/2411.11922
👉Repo https://github.com/yangchris11/samurai
👉Project https://yangchris11.github.io/samurai/

🦖Dino-X: Unified Obj-Centric LVM🦖

👉Unified vision model for Open-World Detection, Segmentation, Phrase Grounding, Visual Counting, Pose, Prompt-Free Detection/Recognition, Dense Caption, & more. Demo & API announced 💙

👉Review https://t.ly/CSQon
👉Paper https://lnkd.in/dc44ZM8v
👉Project https://lnkd.in/dehKJVvC
👉Repo https://lnkd.in/df8Kb6iz

🌎All Languages Matter: LMMs vs. 100 Lang.🌎

👉ALM-Bench aims to assess the next generation of massively multilingual multimodal models in a standardized way, pushing the boundaries of LMMs towards better cultural understanding and inclusivity. Code & Dataset 💙

👉Review https://t.ly/VsoJB
👉Paper https://lnkd.in/ddVVZfi2
👉Project https://lnkd.in/dpssaeRq
👉Code https://lnkd.in/dnbaJJE4
👉Dataset https://lnkd.in/drw-_95v

🦙 EdgeCape: SOTA Agnostic Pose 🦙

👉EdgeCap: new SOTA in Category-Agnostic Pose Estimation (CAPE): finding keypoints across diverse object categories using only one or a few annotated support images. Source code released💙

👉Review https://t.ly/4TpAs
👉Paper https://arxiv.org/pdf/2411.16665
👉Project https://orhir.github.io/edge_cape/
👉Code https://github.com/orhir/EdgeCape

🛟 StableAnimator: ID-aware Humans 🛟

👉StableAnimator: first e2e ID-preserving diffusion for HQ videos without any post-processing. Input: single image + sequence of poses. Insane results!

👉Review https://t.ly/JDtL3
👉Paper https://arxiv.org/pdf/2411.17697
👉Project francis-rings.github.io/StableAnimator/
👉Code github.com/Francis-Rings/StableAnimator

🧶SOTA track-by-propagation🧶

👉SambaMOTR is a novel e2e model (based on Samba) for long-range dependencies and interactions between tracklets to handle complex motion patterns / occlusions. Code in Jan. 25 💙

👉Review https://t.ly/QSQ8L
👉Paper arxiv.org/pdf/2410.01806
👉Project sambamotr.github.io/
👉Repo https://lnkd.in/dRDX6nk2

👺HiFiVFS: Extreme Face Swapping👺

👉HiFiVFS: HQ face swapping videos even in extremely challenging scenarios (occlusion, makeup, lights, extreme poses, etc.). Impressive results, no code announced😢

👉Review https://t.ly/ea8dU
👉Paper https://arxiv.org/pdf/2411.18293
👉Project https://cxcx1996.github.io/HiFiVFS

🔥Video Depth without Video Models🔥

👉RollingDepth: turning a single-image latent diffusion model (LDM) into the novel SOTA depth estimator. It works better than dedicated model for depth 🤯 Code under Apache💙

👉Review https://t.ly/R4LqS
👉Paper https://arxiv.org/pdf/2411.19189
👉Project https://rollingdepth.github.io/
👉Repo https://github.com/prs-eth/rollingdepth

⚽Universal Soccer Foundation Model⚽

👉Universal Soccer Video Understanding: SoccerReplay-1988 - the largest multi-modal soccer dataset - and MatchVision - the first vision-lang. foundation models for soccer. Code, dataset & checkpoints to be released💙

👉Review https://t.ly/-X90B
👉Paper https://arxiv.org/pdf/2412.01820
👉Project https://jyrao.github.io/UniSoccer/
👉Repo https://github.com/jyrao/UniSoccer

🌈Motion Prompting Video Generation🌈

👉DeepMind unveils ControlNet, novel video generation model conditioned on spatio-temporally sparse or dense motion trajectories. Amazing results, but no code announced 😢

👉Review https://t.ly/VyKbv
👉Paper arxiv.org/pdf/2412.02700
👉Project motion-prompting.github.io