๋ณธ๋ฌธ ๋ฐ”๋กœ๊ฐ€๊ธฐ

sdf2

[Notable] Explicit Representation VS Implicit Representation 1. Explicit Representation (๋ช…์‹œ์  ํ‘œํ˜„)๐Ÿ” ์ •์˜:Explicit Representation์€ ๋ฐ์ดํ„ฐ๋ฅผ ์ง์ ‘์ ์ด๊ณ  ๊ตฌ์ฒด์ ์œผ๋กœ ํ‘œํ˜„ํ•˜๋Š” ๋ฐฉ์‹์ž…๋‹ˆ๋‹ค.๋ชจ๋ธ์ด ๋‹ค๋ฃจ๋Š” ๊ตฌ์กฐ, ํŠน์„ฑ, ๋ฐ์ดํ„ฐ ํฌ์ธํŠธ ๋“ฑ์ด ๋ช…ํ™•ํ•œ ํ˜•ํƒœ๋กœ ์ •์˜๋ฉ๋‹ˆ๋‹ค.๐Ÿ“Š ์˜ˆ์‹œ:์ด๋ฏธ์ง€ ๋ฐ์ดํ„ฐ: ํ”ฝ์…€ ๊ฐ’์œผ๋กœ ์ด๋ฃจ์–ด์ง„ RGB ์ด๋ฏธ์ง€ ๊ฐ ํ”ฝ์…€์˜ ์ƒ‰์ƒ, ์œ„์น˜๊ฐ€ ์ •ํ™•ํ•˜๊ฒŒ ์ €์žฅ๋จ3D ๋ชจ๋ธ๋ง: ๋ฉ”์‰ฌ(Mesh) ๊ธฐ๋ฐ˜ ๋ชจ๋ธ: ์ (vertex)๊ณผ ๋ฉด(face)์˜ ์ขŒํ‘œ๊ฐ€ ๋ช…ํ™•ํ•˜๊ฒŒ ๊ธฐ๋ก๋จํ†ต๊ณ„ ๋ชจ๋ธ: ๊ฐ€์šฐ์‹œ์•ˆ ๋ถ„ํฌ: ํ‰๊ท (μ)๊ณผ ๋ถ„์‚ฐ(σ²)์ด ๋ช…ํ™•ํ•˜๊ฒŒ ์ •์˜๋จโœ… ์žฅ์ : ์ง๊ด€์ ์ด๊ณ  ํ•ด์„์ด ์‰ฌ์›€ ๋ฐ์ดํ„ฐ๋‚˜ ๊ตฌ์กฐ์˜ ๋ณ€๊ฒฝ์ด ์šฉ์ด ๋ช…ํ™•ํ•œ ์ˆ˜์‹ ๋˜๋Š” ๊ทœ์น™์— ๊ธฐ๋ฐ˜โŒ ๋‹จ์ : ๋ณต์žกํ•œ ๋ฐ์ดํ„ฐ๋ฅผ ํ‘œํ˜„ํ• ์ˆ˜๋ก ๋น„์šฉ์ด ํผ (๋ฉ”๋ชจ๋ฆฌ, ๊ณ„์‚ฐ๋Ÿ‰ ์ฆ๊ฐ€) ๊ณ ์ฐจ์› ๋ฐ์ดํ„ฐ์—์„œ๋Š” ๋น„ํšจ์œจ์ ์ผ ์ˆ˜ .. 2025. 1. 31.
[Paper Review] DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation Abstract1. DeepSDF๋ž€?- ํ•™์Šต ๊ธฐ๋ฐ˜์˜ ์—ฐ์†์  Signed Distance Function (SDF) ํ‘œํ˜„- ํ˜•์ƒ ํด๋ž˜์Šค ์ „์ฒด๋ฅผ ๊ณ ํ’ˆ์งˆ๋กœ ํ‘œํ˜„, ๋ณด๊ฐ„(interpolation), ๋ถˆ์™„์ „ ๋ฐ์ดํ„ฐ ๋ณต์› ๊ฐ€๋Šฅ2. ํ‘œํ˜„ ๋ฐฉ์‹- ๋ถ€ํ”ผ ํ•„๋“œ์—์„œ ์ ์˜ ํฌ๊ธฐ: ํ‘œ๋ฉด ๊ฒฝ๊ณ„๊นŒ์ง€์˜ ๊ฑฐ๋ฆฌ- ๋ถ€ํ˜ธ: ํ˜•์ƒ ๋‚ด๋ถ€(-) ๋˜๋Š” ์™ธ๋ถ€(+)- ๊ฒฝ๊ณ„๋Š” ํ•จ์ˆ˜์˜ 0-level-set ์œผ๋กœ ์•”๋ฌต์ ์œผ๋กœ ์ธ์ฝ”๋”ฉ3. ๊ธฐ์กด SDF ์™€ ์ฐจ์ด์ - ๊ธฐ์กด SDF ๋Š” ๋‹จ์ผ ํ˜•์ƒ ํ‘œํ˜„- DeepSDF ๋Š” ํ˜•์ƒ ํด๋ž˜์Šค ์ „์ฒด๋ฅผ ํ•™์Šตํ•˜๊ณ  ํ‘œํ˜„ ๊ฐ€๋Šฅ4. ์„ฑ๊ณผ- 3D ํ˜•์ƒ ํ‘œํ˜„๊ณผ ๋ณต์›์—์„œ ์ตœ์ฒจ๋‹จ ์„ฑ๋Šฅ- ๋ชจ๋ธ ํฌ๊ธฐ๋ฅผ ๊ธฐ์กด ๋Œ€๋น„ 10๋ฐฐ ๊ฐ์†Œ Introduction1. ๋ฌธ์ œ ์ •์˜: 3D ๋”ฅ๋Ÿฌ๋‹ ๋ชจ๋ธ์€ ๊ธฐ์กด ๋ฐฉ์‹์—์„œ ๊ณต๊ฐ„ ๋ฐ ์‹œ๊ฐ„ ๋ณต์žก๋„ ์ฆ๊ฐ€, ์ •์ (vertex) .. 2024. 12. 9.

ํ‹ฐ์Šคํ† ๋ฆฌํˆด๋ฐ”