2 l Michiya Abe l ܦྺ l 2019 ɿम࢜ʢใཧֶʣ l 2019 ~ ɿࣗಈӡస͚ը૾ೝࣝͷݚڀ։ൃ l ମݕग़ɾ࿏ೝࣝͷϞσϧͷ։ൃ l ϞσϧͷྔࢠԽɼΤοδͰͷߴԽ l ͖ͳͷ l ςΩετΤσΟλʢNeovimʣ l Ϊλʔʢॳ৺ऀʣ ࣗݾհ Twitter: @abemii_ Blog: https://abemii.hatenablog.com/ ˞ ൃද༰ॴଐػؔͱҰؔ͠·ͤΜ
18 ֶशՄೳͳଟॏղ૾ಛάϦουΛ NNFͱΈ߹ΘͤΔ େҬಛͱہॴಛΛཱ྆ͨ͠ޮతͳಛάϦου ΫΤϦϙΠϯτ ଟॏղ૾ಛάϦου ֤ϨϕϧͰ τϦϦχΞิؒ ࢹϕΫτϧͱ݁߹ͯ͠ɼ .-1IFBEͰॲཧ MLP ジオ メト リ 特徴 記述 ⼦ l େҬతͳίϯςΫετͱɼࡉ͔͍ಛͷ྆ํΛΤϯίʔυͰ͖Δ l MLP ϔουͷେ͖͞Λখ͘͞Ͱ͖ɼਪ࣌ؒΛݮΒͤΔ l ࣮ࡍʹɼ Instant-NGP [2] ͷΑ͏ͳɼଟॏղ૾ϋογϡΤϯίʔσΟϯάͰ࣮ ͞Ε͍ͯΔΒ͍͠ʢ͋·Γࡉ͔͍ใॻ͍͍ͯͳ͍ʣ [2] Thomas Muller, Alex Evans, Christoph Schied, and Alexander Keller. Instant neural graphics primitives with a multiresolution hash encoding. In SIGGRAPH, 2022.
19 ܭଌं͕྆௨ա͖ͯͨ͠ྖҬΛ੩తͳഎܠͱಈతͳ ΞΫλʔʹ͚ͯϞσϧԽ͢Δ l ผʑͰ 3D ۭؒϘϦϡʔϜΛఆٛ l ੩తͳഎܠɿੈք࠲ඪܥͰදݱ l ಈతͳΞΫλʔɿͦΕͧΕͷମத৺࠲ඪܥͰදݱ l ͦΕͧΕผʑͷଟॏղ૾ಛάϦουͱ NFF ͰϞσϧԽ͢Δ l ֤ΞΫλʔͷ 3D ϞʔγϣϯΛΓ͠ɼ ܗঢ়ͱ֎؍ͷදݱʹूதͰ͖Δ l ܗঢ়ͷදݱʹɼූ߸͖ڑؔ (SDF) Λ͏ɽ ߹χϡʔϥϧදݱ Dynamic Actors Static Background B ݁ߏͳ͕͍ڑߦ → ޮతͳදݱ͕ඞཁ SDV A1 A2 ɿA1 ͷي ɿA2 ͷي
24 l LiDAR ܈ɿ3DͷҐஔʢਂʣ+ ڧʢࣹʣ ϚϧνϞʔμϧͳηϯαγϛϡϨʔγϣϯʢΧϝϥը૾ + LiDAR ܈ʣ ਂ αϯϓϧ͞Εͨ 3D ͷਂͷظ Λܭࢉ͠ɼਂͷܭଌΛγϛϡϨʔτ ͢Δ MLP 視点 多重解像度特徴 グリッド MLP ηϯαத৺ o Ray ํ d Ray ʹԊͬͨ 3D ͷϙΠϯτΛ நग़͠ɼNNF ʹΑΓಛ f ͱ δΦϝτϦ s ΛಘΔ ڧ ϘϦϡʔϜϨϯμϦϯάͨ݁͠ՌΛ MLPͷσίʔμͰॲཧͯ͠༧ଌ （同じ）
40 l ࣮ੈքͷγφϦΦΛ׆༻ͯ͠ɼࣗγεςϜͷςετʹ༻Ͱ͖Δຊ ͦͬ͘ΓͷԾੈքΛߏங l ΧϝϥɾLiDAR ͷγʔέϯεΛೖྗͱ͠ɼಈతͳΞΫλʔͱ੩తͳഎܠΛ ղɾ࠶ߏͰ͖ΔχϡʔϥϧηϯαγϛϡϨʔλ l υϝΠϯΪϟοϓ͕খ͘͞ɼੜ͞Εͨ৽͍͠γφϦΦʹΑΔ Closed- loop ςετʹ༻Մೳ l ࠓޙͷ՝ɾݶք l র໌݅ɾఱީ݅ͷରԠ l ଟؔઅΞΫλʔͷରԠ ·ͱΊ [4] Jingkang Wang, Siva Manivasagam, Yun Chen, Ze Yang , Ioan Andrei Bârsan, Anqi Joyce Yang, Wei–Chiu Ma, Raquel Urtasun. CADSim: Robust and Scalable in-the-wild 3D Reconstruction for Controllable Sensor Simulation. In CoRL, 2022. ଟؔઅΞΫλʔͷྫ [4] ΑΓҾ༻
41 1. Raquel Urtasun. Next Generation Simulation for the Safe Development and Deployment of Self-Driving Technology. In CVPR Vision- Centric Autonomous Driving workshop, 2023. https://www.youtube.com/watch?v=0RjF9xbkiAY 2. Thomas Muller, Alex Evans, Christoph Schied, and Alexander Keller. Instant neural graphics primitives with a multiresolution hash encoding. In SIGGRAPH, 2022. 3. Pengchuan Xiao, Zhenlei Shao, Steven Hao, Zishuo Zhang, Xiaolin Chai, Judy Jiao, Zesong Li, Jian Wu, Kai Sun, Kun Jiang, et al. Pandaset: Advanced sensor suite dataset for autonomous driving. In ITSC, 2021 https://scale.com/open-av-datasets/pandaset 4. Jingkang Wang, Siva Manivasagam, Yun Chen, Ze Yang , Ioan Andrei Bârsan, Anqi Joyce Yang, Wei–Chiu Ma, Raquel Urtasun. CADSim: Robust and Scalable in-the-wild 3D Reconstruction for Controllable Sensor Simulation. In CoRL, 2022. 5. Julian Ost, Fahim Mannan, Nils Thuerey, Julian Knodt, and Felix Heide. Neural scene graphs for dynamic scenes. In CVPR, 2021. 6. Gernot Riegler and Vladlen Koltun. Free view synthesis. In ECCV, 2020. ࢀߟจݙ
abemii
kyoun
isayan
cheerfularge
ahspragu
yukizenimoto
eumesy
satotaichi
tmats
mickey_kubo
kinakomoti321
chokkan
yumulab
panda_program
jasonvnalue
jnunemaker
eitanlees
michaelherold
andyhume
jmmastey
62gerente
lara
denniskardys
afnizarnur
chrislema